2.1 The surface- and deep-syntactic structures

SSyntSs and DSyntSs are directed, node- and edge-labeled dependency trees with standard feature-value structures (Kasper and Rounds Reference Kasper and Rounds1986) as node labels and dependency relations as edge labels. Both differ, however, with respect to the abstraction of linguistic information: DSyntSs capture predicate-argument relations between meaning-bearing lexical items, while these relations are not captured by SSyntSs. At the same time, DSyntSs maintain the sentence structure (as SSyntSs do).

The features of the node labels in SSyntSs are lex, which captures the name of the lexical item, and ‘syntactic grammemes’ of this name, i.e., number, gender, case, person for nouns and tense, mood and finiteness for verbs. The value of lex can be any (either full or functional) lexical item. The edge labels of a SSyntS are grammatical functions ‘subj’, ‘dobj’, ‘det’, ‘modif’, etc. In other words, SSyntSs are syntactic structures of the kind as encountered in the standard dependency treebanks: dependency version of the Penn Treebank (PTB) (Johansson and Nugues Reference Johansson, Nugues, Nivre, Kaalep, Muischnek and Koit2007) for English, Prague Dependency Treebank for Czech (Hajič et al. Reference Hajič, Panevová, Hajičová, Sgall, Pajas, Štěpánek, Havelka, Mikulová and Žabokrtský2006), AnCora for Spanish (Taulé, Martí and Recasens Reference Taulé, Martí and Recasens2008), Copenhagen Dependency Treebank for Danish (Buch-Kromann Reference Buch-Kromann2003), etc. In formal terms, which we need for the outline of the transduction below, a SSyntS is defined as follows:

Definition 1 (SSyntS)

An SSyntS of a language ${\cal L}$ is a quintuple T_SS = ⟨N, A, λ _{ls → n} , ρ _{rs → a} , γ _{n → g} ⟩ defined over all lexical items L of ${\cal L}$ , the set of syntactic grammemes G_synt , and the set of grammatical functions R_gr , where

• • the set N of nodes and the set A of directed arcs form a connected tree,

• • λ _{ls → n} assigns to each n ∈ N an l_s ∈ L,

• • ρ _{rs → a} assigns to each a ∈ A an r ∈ R_gr ,

• • γ _{n → g} assigns to each λ _{ls → n} (n) a set of grammemes G_t ∈ G_synt .

The top structure in Figure 3 shows a sample SSyntS, where the feature-value information for three nodes is made explicit for illustration. A more common graphical representation of a SSyntS (which does not show explicitly the features and their corresponding values) is displayed in Figure 4(a).

Fig. 3.

SSyntS (top) and DSyntS (bottom) for the sentence The producer thinks that the new song will be successful soon.

Fig. 4.

SSyntS and DSyntS for the sentence Almost 1.2 million jobs have been created by the state in that time.

The features of the node labels in DSyntSs are lex and ‘semantic grammemes’ of the value of lex, i.e., number and definiteness for nouns and tense, finiteness, mood, voice and aspect for verbs.Footnote ⁵ In contrast to lex in SSyntS, DSyntS's lex can be any full, but not a functional lexeme. In accordance with this restriction, in the case of look after a person, after will not appear in the corresponding DSyntS since it is a functional (or governed) preposition. In contrast, after in leave after the meeting will remain in the DSyntS because there it has its own meaning of ‘succession in time’. The edge labels of a DSyntS are ‘deep-syntactic’ relations I,. . .,VI, ATTR, COORD, APPEND. ‘I’,. . .,‘VI’ are argument relations, analogous to A0, A1, etc. in the PropBank annotation. ‘ATTR’ subsumes all (circumstantial) ARGM-x PropBank relations as well as the modifier relations not captured by the PropBank and FrameNet annotations. ‘COORD’ is the coordinative relation as in: John-COORD → and-II → Mary, publish-COORD → or-II → perish, and so on. APPEND subsumes all parentheticals, interjections, direct addresses, etc., as, e.g., in Listen, John!: listen-APPEND → John. DSyntSs thus show a strong similarity with PropBank structures, with four important differences: (i) their lexical labels are not disambiguated;Footnote ⁶ (ii) instead of circumstantial thematic roles of the kind ARGM-LOC, ARGM-DIR, etc. they use a unique ATTR relation; (iii) they capture all existing dependencies between meaning-bearing lexical nodes and (iv) they are connected. Formally, a DSyntS is defined as follows:

Definition 2 (DSyntS)

A DSyntS of a language ${\cal L}$ is a quintuple T_DS = ⟨N, A, λ _{ls → n} , ρ _{rs → a} , γ _{n → g} ⟩ defined over the full lexical items L_d of ${\cal L}$ , the set of semantic grammemes G_sem , and the set of deep-syntactic relations R_dsynt , where

• • the set N of nodes and the set A of directed arcs form a connected tree,

• • λ _{ls → n} assigns to each n ∈ N an l_s ∈ L_d ,

• • ρ _{rs → a} assigns to each a ∈ A an r ∈ R_dsynt ,

• • γ _{n → g} assigns to each λ _{ls → n} (n) a set of grammemes G_t ∈ G_sem .

The bottom structure in Figures 3 and 4(b) show examples of DSyntSs.

As mentioned, a number of other annotations have resemblance with DSyntSs. In particular, as already pointed out, DSyntSs show some resemblance but also some important differences with PropBank structures, mainly due to the fact that the latter concern phrasal chunks and not individual nodes. Figure 5 shows the PropBank structure that corresponds to the SSyntS and DSyntS in Figure 4. The square brackets in the PropBank structure indicate the constituents that implicitly form part of the arguments of A1 and AM-TMP, respectively.

Fig. 5.

PropBank structure of the sentence Almost 1.2 million jobs have been created by the state in that time.

The target structures of the SemEval 2014 shared task on Broad-Coverage Semantic Dependency Parsing (Oepen et al. Reference Oepen, Kuhlmann, Miyao, Zeman, Flickinger, Hajic, Ivanova and Zhang2014) also show some similarities with DSyntSs. For instance, the DELPH-IN annotation, which is a rough conversion of the Minimal Recursion Semantics treebank (Oepen and Lønning Reference Oepen and Lønning2006) into bi-lexical dependencies, also captures the lexical argument (or valency) structure and eliminates some functional elements (such as be copula and prepositions). The Enju annotation (Miyao Reference Miyao2006) is a pure predicate-argument graph over all the words of a sentence. However, it distinguishes arguments of functional elements (auxiliaries, infinitive and dative TO, THAT, WHETHER, FOR complementizers, passive BY) in that they are attached to the semantic heads of these elements (rather than to the elements themselves). This facilitates the disregard of functional elements – as in DSyntSs (cf. Ivanova et al. (Reference Ivanova, Oepen, Øvrelid and Flickinger2012) for a more complete overview of Enju and DELPH-IN).

The degree of ‘semanticity’ of DSyntSs can be directly compared to Prague's tectogrammatical structures (PDT-tecto (Hajič et al. Reference Hajič, Panevová, Hajičová, Sgall, Pajas, Štěpánek, Havelka, Mikulová and Žabokrtský2006)), which contain autosemantic words only. Synsemantic elements such as determiners, auxiliaries, prepositions and conjunctions are not kept in tectogrammatical structures. Thanks to the distinction between argumental and non-argumental edges, tectogrammatical structures are trees, not graphs. That is, as in the DSyntSs, they maintain the syntactic structure of the sentence. The main differences between DSyntSs and tectogrammatical structures are: (i) in tectogrammatical structures, no distinction is made between governed and non-governed prepositions and conjunctions, and (ii) in tectogrammatical structures, the vocabulary used for edge labels emphasizes ‘semantic’ content over predicate-argument information. For instance, a label like ADDR (addressee) indicates that the dependent is an argument of its governor, but does not say which slot is occupied in the valency frame of the latter. At the same time, this tag indicates that the dependent is the recipient of a message, which a simple ARG2 label for instance does not encode.Footnote ⁷ DSyntSs, on the other hand, have the advantage to directly encode predicate-argument structures and thus be straightforwardly connected to existing lexical resources such as PropBank or NomBank, and through these to deeper representation such as VerbNet (Schuler Reference Schuler2005) and FrameNet structures; see Palmer (Reference Palmer2009).

Although the annotations are not really of the same nature, DSyntSs can be furthermore contrasted to the Collapsed Stanford Dependencies (SD) (de Marneffe and Manning Reference de Marneffe and Manning2008). Collapsed SDs differ from DSyntSs (apart from the fact that that they may be (sometimes) disconnected graphs) in that: (i) in the same fashion as in the Prague Dependency Treebank, they collapse only (but all) prepositions, conjunctions and possessive clitics, whereas DSyntSs omit all functional nodes (all auxiliaries, some determiners, and some prepositions and conjunctions); (ii) they do not involve any removal of (syntactic) information since the meaning of the preposition remains encoded in the label of the collapsed dependency, while DSyntSs omit or generalize the purely functional elements; (iii) they do not add semantic information compared to the surface annotation. That is, Collapsed SDs keep the surface-syntactic information, representing it in a different format, while DSyntSs keep only deep-syntactic information. Consider Figure 6 for illustration.Footnote ⁸

Fig. 6.

Collapsed Stanford dependency structure of the sentence Almost 1.2 million jobs have been created by the state in that time.

As in all mentioned annotations (except in SD), the opposition between active and passive voice is neutralized in the DSynSs – for instance, both the first object of an active verb and the subject of a passive verb are annotated as second arguments. As in PDT-tecto, PropBank and SD, in DSyntSs multi-word expressions (MWEs) are handled through a specific dependency relation; in DRS and DELPH-IN, special predicates exist, which take as arguments the components of a MWE, while in Enju, MWEs are not annotated. In our current version of the DSyntSs (as in SD, DRS, DELPH-IN, and Enju), predicates are not disambiguated and light verb constructions, which are the most common type of MWEs, are annotated as regular constructions. In contrast, in the PropBank and PDT-tecto annotations, verbs and nouns are disambiguated, and an independent resource with lexical units and their valency frames is compiled (PropBank lexicon and PDT-VALLEX). In PropBank and PDT-tecto, light verb constructions are also annotated: as MWEs in PDT-tecto, and as independent lexical units in the PropBank lexicon. Finally, in DSyntSs, argument sharing is not represented, since at this level the structures must be trees and one node can thus receive one and only one incoming arc. In the Meaning-Text framework, argument sharing is made explicit at the semantic layer, where the structures are predicate-argument graphs. The PDT-tecto annotation is also arborescent, but its authors made the choice to annotate argument sharing by duplicating shared arguments in the tree for control and coordinate structures.Footnote ⁹ PropBank, SD, DRS, DELPH-IN and Enju, are graph representations, so shared arguments in coordinate and control constructions are not an issue. However, in PropBank and SD, special relations are used in some case of control constructions (and other phenomena), respectively C-AM and xsubj relations.

2.2 SSyntS–DSyntS correspondences

The implementation of the transduction from SSyntS to DSyntS requires a prior detailed analysis of the correspondences between elements of SSyntS and DSyntS. Let us thus discuss the correspondences between the two types of structures, based on the example in Figure 7 (in which the grammemes are not shown for the sake of clarity); we use a Spanish example (instead of, e.g., an English one) because it allows us to illustrate all relevant phenomena.

Fig. 7.

SSyntS and DSyntS of the sentence el profesor dice que se quejan mucho ‘the professor says that they complain a lot’.

The following correspondences between the SSyntS S_ss and DSyntS S_ds of a sentence need to be taken into account during the SSyntS–DSyntS transduction:Footnote ¹⁰

1. (i) A node in S_ss is a node in S_ds (Figure 8):

   The node mucho ‘a-lot’ has a single correspondent in the DSyntS. This is also the case of the node profesor.

2. (ii) A relation in S_ss corresponds to a relation in S_ds (Figure 9):

   The SSynt relation subj is mapped to the DSynt relation I. Note that the relation-to-relation mapping is not necessarily unique. Thus, subj is mapped to II (rather than to I) if the verb in the SSyntS is in passive.

3. (iii) A fragment of the S_ss tree corresponds to a single node in S_ds (Figure 10):

   The words dice ‘say’ and que ‘that’ and the dependency between them (dobj) correspond to one single node in DSynt (decir ‘say’); in other words, que ‘that’ is not reflected in the DSyntS.

4. (iv) A relation with a dependent or governor node in S_ss is a grammeme in S_ds (Figure 11):

   The relation det and its dependent, the definite determiner el ‘the’, are stored in the DSyntS as the grammeme of definiteness associated to the node profesor ‘professor’. Similarly, the auxiliary relations and their governors correspond to a grammeme of voice, tense, or aspect on the node of the dependent verb.Footnote ¹¹

5. (v) A grammeme in S_ss is a grammeme in S_ds (Figure 12):

   Number grammemes are maintained on nodes which can carry semantic number (that is, on nodes which do not have a number only for agreement reasons, as it can be the case for verbs in English, verbs, determiners and adjectives in Spanish and other languages, etc.), such as singular number on the node profesor ‘professor’. Other grammemes, such as those of tense, mood, or finiteness are mapped the same way.

6. (vi) A node in S_ss is conflated with another node in S_ds (Figure 13):

   For this correspondence, the reflexive pronoun se ‘itself’/‘each other’ is part of the lemma of the verb in the DSyntS. In the SSyntS, it is separated in order to produce the sentence se quejan, lit. ‘themselves they-complain’.

7. (vii) A node in S_ds has no correspondence in S_ss (Figure 14):

Fig. 8.

A node in S_ss is a node in S_ds .

Fig. 9.

A relation in S_ss corresponds to a relation in S_ds .

Fig. 10.

A fragment of the S_ss tree corresponds to a single node in S_ds .

Fig. 11.

A relation with a dependent or governor node in S_ss is a grammeme in S_ds .

Fig. 12.

A grammeme in S_ss is a grammeme in S_ds .

Fig. 13.

A node in S_ss is conflated with another node in S_ds .

Fig. 14.

A node in S_ds has no correspondence in S_ss .

In Spanish, which is a pro-drop language, the subject of a finite verb does not need to be realized, even though there is a node at the DSynt level which accounts for the agreement found on the verb, for instance (third person plural in this case).

3.1 Principles of the SSyntS–DSyntS transduction

In the above list of SSynt-DSynt correspondences, the grammeme correspondences (iv) and (v) and the ‘pseudo’ correspondences in (vi) and (vii) are few or idiosyncratic and are best handled in a rule-based post-processing stage; see Section 3.5. The main task of the SSyntS–DSyntS transducer is thus to cope with the correspondences (i)–(iii). For this purpose, we consider SSyntS and DSyntS trees as two-dimensional matrices I = N × N (with N as the set of nodes {1, . . ., m} of a given tree and $I(i, j) = \rho _{{r_s}{\rightarrow} a}(n_i, n_j)$ if n_i , n_j ∈ N and (n_i , n_j ) = a ∈ A (i, j = 1, . . ., m; i ≠ j) and I(i, j) = 0 otherwise.Footnote ¹² That is, for a given SSyntS, I(i, j) contains in the cell (i, j), i, j = 1, . . ., m (with i ≠ j) the name of the SSynt-relation that is encountered in the given tree between the nodes n_i and n_j . If no relation holds between n_i and n_j , the cell I(i, j) contains ‘0’. In analogy, for a given DSyntS, the cells contain DSyntS-relations between the corresponding nodes.

Starting from the matrix I_s of a given SSyntS, the task is therefore to obtain the matrix I_d of the corresponding DSyntS, that is, to identify correspondences between i_s respectively j_s , (i_s , j_s ) and groups of (i_s , j_s ) of I_s with i_d respectively j_d and (i_d , j_d ) of I_d ; see (i)–(iii) above. In other words, the task consists in identifying and removing all functional lexemes, and attach correctly the remaining nodes between them.Footnote ¹³

As already the projection of a chain of tokens onto an SSyntS, the SSyntS–DSyntS projection can be viewed as a classification task. However, while the ‘chain → surface-syntactic tree’ projection is isomorphic, the latter is not (see (iii)). In order to make it appear as an isomorphic projection, it is convenient to interpret SSyntS and the targeted DSyntS as collection of hypernodes; cf. Definition 3:

Definition 3 (Hypernode)

Given a SSyntS S_s with its matrix I_s and a DSyntS S_d with its matrix I_d , a node partition p (with ∣p∣ ⩾ 1) of I_s /I_d is a hypernode h _si / h _di iff p corresponds to a partition p′ (with ∣p′∣ ⩾ 1) of S_d /S_s .

In other words, a SSyntS hypernode, known as syntagm in linguistics, is any SSyntS configuration with a cardinality ⩾ 1 that corresponds to a single DSyntS node. The notion of hypernode is quite generic. It subsumes several types of correspondences discussed in Section 2.2 (namely, (i), (iii), (iv) and (vi)). For instance, dice que ‘says that’, el profesor ‘the professor’, and se quejan ‘(they) complain’ from the example above constitute hypernodes. Hypernodes can also contain more than two nodes, as in the case of more complex analytical verb forms, e.g., ha sido invitado ‘he-has been invited’, which corresponds to the node invitar ‘invite’ in the DSyntS.

In this way, the SSyntS–DSyntS correspondence boils down to a correspondence between individual hypernodes and between individual arcs, such that the transduction embraces the following three (classification) subtasks: (i) hypernode identification, (ii) DSynt tree reconstruction and (iii) DSynt arc labeling, which are completed by (iv) post-processing.

3.2 Hypernode identification

The hypernode identification consists of a binary classification of the nodes of a given SSyntS as nodes that form a hypernode of cardinality 1 (i.e., nodes that have a one-to-one correspondence to a node in the DSyntS) versus nodes that form part of a hypernode of cardinality > 1. In practice, hypernodes of the first type (henceforth, ‘type 1’ or ‘h1’) will be formed by: (1) noun nodes that do not govern (in)definite determiner or functional preposition nodes, (2) full verb nodes that are not governed by any auxiliary verb nodes and that do not govern any functional preposition node and (3) adjective, adverbial, and semantic preposition nodes which do not govern functional preposition nodes.

Hypernodes of the second type (henceforth, ‘type 2’ or ‘h2’) will be formed by: (1) noun nodes + (in)definite determiner + functional preposition nodes they govern, (2) verb nodes + auxiliary nodes they are governed by + functional preposition nodes they govern + reflexive pronoun se ‘oneself’ when it is part of the lemma of the verb and (3) adjective, adverbial, and semantic preposition nodes + functional preposition nodes they govern.

The following sentence shows different examples of hypernodes of type 1 (h1) and type 2 (h2):

1. (2) [El capitán de] _h2 [la embarcación] _h2 [se ha puesto a] _h2 [cantar] _h1 [cuando] _h1 [ha visto a] _h2 [cuatro] _h1 [delfines] _h1 [adultos] _h1 [saltar] _h1 [cerca de] _h2 [nosotros] _h1.

   ‘[The captain of] _h2 [the boat] _h2 [(reflexive+has) started to] _h2 [sing] _h1 [when] _h1 [he-has seen prep] _h2 [four] _h1 [dolphins] _h1 [adults] _h1 [jump] _h1 [next to] _h2 [us] _h1.’

3.3 DSynt tree reconstruction

The outcome of the hypernode identification stage is thus the set H_s = H _{s ∣p∣ = 1} ∪H _{s ∣p∣ > 1} of hypernodes of two types. With this set at hand, we can define an isomorphic function τ: H_s → H _{d ∣p∣ = 1} (with h_d ∈ H _{d ∣p∣ = 1} consisting of n_d ∈ N_ds , i.e., the set of nodes of the target DSyntS). τ is the identity function for h_s ∈ H _{s ∣p∣ = 1} . For h_s ∈ H _{s ∣p∣ > 1} , τ maps the functional nodes in h_s onto grammemes (attribute-value tags) of the meaning-bearing node in h_d and identifies the meaning-bearing node as governor. Some of the dependencies of the obtained nodes n_d ∈ N_ds can be recovered from the dependencies of their sources. Due to the node removals (e.g., the projection of functional nodes to grammemes), some dependencies will be also missing and must be introduced. The algorithm in Figure 15 recalculates the dependencies for the target DSyntS S_d , starting from the matrix I_s of SSyntS S_s to obtain a connected tree.

Fig. 15.

DSyntS tree reconstruction algorithm.

BestHead recursively ascends S_s from a given node n_i until it encounters one or several governor nodes n_d ∈ N_ds . In case of several encountered governor nodes, the one which governs the highest frequency dependency is returned. Consider Figure 16 for illustration.

Fig. 16.

A sentence in its surface representation that shows two paths: [dep₁] + [dep₂] + [dep₃] for the node₃ and [dep₁] + [dep₄] for node₄ . The nodes governor, node₃ and node₄ are kept in the deep structure. The other nodes (node₁ and node₂ ) are not included in the deep structure. The system has to decide whether node₃ or node₄ are attached to the governor.

3.4 DSynt arc labeling

The tree reconstruction stage produces a ‘hybrid’ connected dependency tree S _{s → d} with DSynt nodes N_ds , and arcs A_s labeled by SSynt relation labels (cf. left part of Figure 17), i.e., a matrix I ⁻, whose cells (i, j) contain SSynt labels for all n_i , n_j ∈ N_ds : (n_i , n_j ) ∈ A_s and ‘0’ otherwise. The next and last stage of SSynt-to-DSyntS transduction is thus the projection of SSynt relation labels of S _{s → d} to their corresponding DSynt labels, or, in other words, the mapping of I ⁻ to I_d of the target DSyntS (see Tables 2 and 3 for concrete examples).

Fig. 17.

Input (left) and output (right) of DSynt arc relabeling.

There are some labels that have a direct transduction (see Table 2 for direct SSynt-DSynt label correspondences in Spanish), while others have several candidates. For instance, and as shown in Table 3 for Spanish, the labels coord and copred are always transduced to COORD and ATTR respectively, while obl_obj may be mapped to II, III, IV or VI, depending on the other dependents of the governor of the current node. This is why it is necessary to include higher-order features based on the siblings of the node that is about to be transduced. Figure 17 shows an example of the relabeling: on the left side of the figure, the dependency labels are superficial (dep _x ), whereas on the right side of the figure, the labels are the ones usually found in a DSyntS (dep _Deepx ).

The system learns the SSynt-to-DSynt label projection (in training time) in order to be able to infer it during the test time. The training procedure outputs a multi-class classifier that detects the best DSynt label for each node, taking into account the features that are included in the procedure. Again, this module allows for two kinds of features: local features related to a node and higher-order features related to the governor node of a node that is being processed and features related to the sibling nodes.

3.5 Postprocessing

As mentioned in Section 2, there is a limited number of idiosyncratic correspondences between elements of SSyntS and DSyntS. The correspondences (iv–vii), depicted in Section 2.2 can be straightforwardly handled by a rule-based post-processor because (a) they are non-ambiguous, i.e., a↔b, c↔b⇒a = c∧a↔b, a↔d⇒b = d, and (b) they are few. The rule-based post-processor creates/copies grammemes and creates respectively collapses some nodes in the DSyntS:

1. (1) Tense and voice grammemes are introduced for verbal lexemes in accordance with the corresponding SSynt dependency relation (e.g., analyt_fut gives rise to ‘tense=FUT(ure)’, analyt_perf to ‘tense=PAST’, analyt_pass to ‘voice=PASS(ive)’, etc.); definiteness grammemes are introduced for nominal lexemes (e.g., the ← det- gives rise to ‘def=DEF’).

2. (2) If a number or tense grammeme is already assigned to a node n_s in the SSyntS, it is copied to the node n_d corresponding to n_s in the DSyntS.

3. (3) A reflexive verb particle that is part of the verb lemma (as e.g., se in Spanish or si in Italian) or a pronoun (as e.g., sich in German) and its verbal governor in the SSyntS are collapsed in the DSyntS into a single node.

4. (4) If a pronoun in the SSyntS of a pro-drop language is omitted, a pronoun node is created and related to its verbal governor in the DSyntS. So far, this case has been implemented only for the zero subject in Spanish, for which the pronoun node is created, furnished with the number and person grammemes derived from the SSyntS and related to its verbal governor by an actantial relation which depends on the voice of the verb: I for active and II for passive, respectively.

4.1 The SSyntS and DSyntS treebanks

We carried out experiments on Spanish, English and Chinese.Footnote ¹⁴

For Spanish, we use the AnCora-UPF SSyntS and DSyntS treebanks (Mille, Burga and Wanner 2013) in CoNLL format,Footnote ¹⁵ which we adjusted for our needs. In particular, we removed from the 79-tags SSyntS treebank the semantically and information structure influenced relation tags to obtain an annotation granularity closer to the granularities used for previous parsing experiments (55 relation tags; see Mille et al. (Reference Mille, Burga, Ferraro and Wanner2012)). Unlike, e.g., PTB, in which syntactic (Penn TreeBank) and semantic role (ProbBank/NomBank) annotations are superimposed in the same CoNLL repository, in AnCora-UPF the SSyntSs and DSyntSs are separate treebanks,Footnote ¹⁶ which have been validated manually (Mille et al. Reference Mille, Burga and Wanner2013).

The treebanks have been divided into: (i) a training set (3,036 sentences, 57,665 tokens in the DSyntS treebank and 86,984 tokens in the SSyntS treebank); (ii) a development set (219 sentences, 3,271 tokens in the DSyntS treebank and 4,953 tokens in the SSyntS treebank); (iii) a held-out test set for evaluation (258 sentences, 5,641 tokens in the DSyntS treebank and 8,955 tokens in the SSyntS treebank).

For English, we use the PTB 3 (Marcus et al. Reference Marcus, Santorini, Marcinkiewicz, MacIntyre, Bies, Ferguson, Katz and Schasberger1994) dependency version (Hajič et al. Reference Hajič, Ciaramita, Johansson, Kawahara, Martí, Màrquez, Meyers, Nivre, Padó, Štěpánek, Straňák, Surdeanu, Xue and Zhang2009) as SSynt annotation. To derive from it the DSynt annotation,Footnote ¹⁷ we implemented graph-transduction grammars in the MATE environment (Bohnet and Wanner Reference Bohnet and Wanner2010).Footnote ¹⁸ The derivation removes all determiners, auxiliaries, that complementizers, infinitive markers to, punctuations and functional prepositions of verbs and predicative nouns. In order to obtain a DSynt annotation of a quality that is close to the quality of our annotation of the Spanish corpus, we used existing (manually annotated) lexical resources during the derivation, namely, PropBank (Kingsbury and Palmer Reference Kingsbury and Palmer2002) and NomBank (Meyers et al. Reference Meyers, Reeves, Macleod, Szekely, Zielinska, Young and Grishman2004).Footnote ¹⁹ In these two resources, 11,781 disambiguated predicates (5,577 nouns and 6,204 verbs) are described and their semantic roles are listed. For each of them, an important share of functional prepositions can be retrieved. To access the list of arguments of each predicate and for each argument the list of its functional prepositions, we draw upon two fields of the XML files of these resources: the last word of the field ‘descr’in ‘roles’, and the first word of the field of the corresponding role in ‘example’. In this way, we obtain, for instance, for the lexical unit beg.01 (Figure 19), the preposition from for the semantic role 1, and the preposition for for role 2. From the example field, we also retrieve for for role 2.

Fig. 19.

Sample PropBank entry.

For each disambiguated predicate of PropBank and NomBank, we add a new entry with the semantic roles and associated functional prepositions. The resulting dictionary allows us to obtain a DSynt layer freed from around 25,000 such prepositions.

Table 1 shows the quality of the obtained DSynt layer. The quality figures are based on the comparison of the DSyntSs of 300 sentences (6,979 SSynt and 4,976 DSynt tokens) of the PTB annotated manually with their automatically obtained equivalents. According to our error analysis, most errors of the automatic annotation are due to the fact that during the annotation, the only information that is available concerns verbs and nouns which govern preposition(s). In other words, functional prepositions governed by adjectives, adverbs or prepositions (e.g., thanks to ) cannot be identified automatically. Neither can be identified argument slots in genitive noun compounds, as explained in Sections 4.3.1–3 for Spanish. However, the automatic annotation is still of reasonable quality that allows us to use it for our experiments.

Table 1.

Quality of the automatic annotation of the PTB with the DSyntS layer

For our experiments, we kept the same training and test dataset split as in the CoNLL Shared Task 2009 (Hajič et al. Reference Hajič, Ciaramita, Johansson, Kawahara, Martí, Màrquez, Meyers, Nivre, Padó, Štěpánek, Straňák, Surdeanu, Xue and Zhang2009): 39,279 sentences for the training set and 2,399 sentences for the test set. This meant in the case of the training set 958,167 tokens in the SSyntS treebank and 711,491 tokens in the DSyntS treebank, and in the case of the test set 57,676 tokens in the SSyntS treebank and 42,467 tokens in the DSyntS treebank.

For Chinese, we use the Chinese Dependency Treebank (Xue et al. Reference Xue, Xia, Chiou and Palmer2004), which was mapped to the DSyntSs along the same lines as PTB 3, but using a graph transduction grammar tuned to Chinese syntax and without lexical resources. The mapping removes (i) aspectual markers (PoS AS), (ii) prepositions in beneficiary constructions (PoS BA), in verbal modifier constructions (PoS DER and DEV), in passives (PoS LB), and in verbal and nominal constructions with PoS DEC, DEG, and P in the case of the word jiu, (iii) localizers when they are combined with prepositions, (iv) certain particles (PoS SP and a subclass of MSP) and (v) punctuations.Footnote ²⁰

The Chinese treebank has been divided into a training set of 31,131 sentences (718,716 tokens in the SSyntS treebank and 553,290 tokens in the DSyntS treebank) and a test set of 10,180 sentences (241,247 tokens in the SSyntS treebank and 186,710 tokens in the DSyntS treebank).

4.2 Getting the SSyntS

To obtain the SSyntS of all three languages with which we experiment, we use Bohnet and Nivre (Reference Bohnet and Nivre2012)'s transition-based parser, which combines PoS tagging and syntactic labeled dependency parsing. The parser uses a number of various techniques to obtain competitive accuracy such as beam search, a hash kernel that can employ a large number of features, and a graph-based completion model that re-scores the beam to capture the tree structure in terms of completed structures composed by up to three edges.

The parser was trained in twenty-five training iterations, using in each iteration the model from the preceding iteration for further processing. Given that the parser combines PoS and dependency parsing, we let the parser choose between the two best PoS tags. The threshold for the inclusion of PoS tags was set to a score of 0.25, and the size for the beam of the alternative PoS tags to 4.

4.3 From SSyntS to DSyntS

In what follows, we first present the realization of the SSyntS–DSyntS transducer and then the baseline that we use for the evaluation of the performance of the transducer. Given that we did the main development work on the Spanish treebanks, the examples in this subsection are given for Spanish and the performance reported for the development data set is for Spanish.

4.3.1 SSyntS–DSyntS transducer

As outlined in Section 3, the SSyntS–DSyntS transducer is composed of three main submodules ((1) Hypernode identification, (2) Tree reconstruction and (3) Relation label classification) and a post-processing submodule. Let us discuss each of them separately.

(1) Hypernode identification: For hypernode identification, we trained a binary Support Vector Machine (SVM) with polynomial kernel from The library for Support Vector Machines (LIBSVM) (Chang and Lin Reference Chang and Lin2001). The SVM allows for both features that are related to the processed node and higher-order features, which can be related to the governor node of the processed node or to its sibling nodes. After several feature selection trials, we chose the following features for each node n:

• • lemma or stem of the label of n,

• • label of the relation between n and its governor,

• • surface PoS of n's label,Footnote ²¹

• • label of the relation between n's governor to its own governor,

• • surface PoS of the label of n’ governor node.

After an optimization round of the parameters available in the SVM implementation, the hypernode identification achieved over the Spanish gold development set 99.78% precision and 99.02% recall (and thus 99.4% F1).Footnote ²² That is, only very few hypernodes are not identified correctly. The main (if not the only) error source are governed prepositions; cf. Section 2: the classifier has to learn when to assign a preposition an own hypernode (i.e., when it is lexically meaning-bearing) and when it should be included into the hypernode of the verb/noun (i.e., when it is functional). Our interpretation is that the features we use for this task are appropriate, but that the training data set is too small. As a result, some prepositions are erroneously removed from or left in the DSyntS.

(2) Tree reconstruction: The implementation of the tree reconstruction module shows an unlabeled dependency attachment precision of 98.18% and an unlabeled dependency attachment recall of 97.43% over the Spanish gold development set. Most of the errors produced by this module have their origin in the previous module, that is, in the hypernode identification. When a node has been incorrectly removed, the module errs in the attachment because it cannot use the node in question as the destination or the origin of a dependency, as it is the case in the gold-standard annotation; cf. Figure 20.Footnote ²³

Fig. 20.

Sample gold-standard and predicted DSyntSs: node erroneously removed from the DSyntS.

When a node has erroneously not been removed, no dependencies between its governor and its dependent can be established since DSyntS must remain a tree (which gives the same LAS and UAS errors as when a node has been erroneously removed); cf. Figure 21.

Fig. 21.

Sample gold-standard and predicted DSyntSs: node erroneously left in the DSyntS.

(3) Relation label classification: For relation label classification, we use a multi-class linear SVM. The label classification procedure depends on the concrete annotation schemata of the SSyntS and DSyntS treebanks on which the parser is trained. Some DSynt relation labels may be easier to derive from the original SSyntS relation labels than others. In Tables 2 and 3, we summarize the DSynt relation label derivation for the Spanish treebank.Footnote ²⁴ Table 2 lists all Spanish SSynt relation labels that have a straightforward mapping to DSyntS relation labels, i.e., (i) neither their dependent nor their governor are removed, and (ii) the SSyntS label always maps to the same DSynt label. Table 3 shows SSyntS relation–DSyntS relation label correspondences that are not straightforward.

Table 2.

Straightforward SSynt to DSyntS DepRel mappings (Spanish)

Table 3.

Complex SSyntS to DSyntS mappings (Spanish); ‘Dep’ = ‘dependent’, ‘Gov’ = ‘governor’, ‘DepRel’ = ‘DSynt dependency relation’

Given that SSyntS is highly language-dependent, the SSyntS–DSyntS mappings must necessarily capture these idiosyncrasies. For instance, for Spanish as a pro-drop language we need to create in the DSyntS nodes that stand for zero subjects (i.e., subjects that do not appear in the SSyntS). Since the data-driven hypernode classifier only removes or keeps nodes, we implemented a simple rule-based approach for node creation. The system adds a node in the DSyntS when there is a finite verb that does not have a dependent which is a subject. This new node inherits the person and number from the verbal governor. This strategy is fully applicable to other languages as well since the system only needs as input the verbal PoS tag and the subjectival dependency relation.

The final set of features selected for label classification includes:

• • lemma of the dependent node,

• • dependency relation to the governor of the dependent node,

• • dependency relation label of the governor node to its own governor,

• • dependency relation to the governor of the sibling nodes of the dependent node, if any.

After an optimization round of the parameters set of the SVM model, relation labeling achieved 94.00% label precision and 93.28% label recall on the Spanish development set. The recall is calculated considering all the nodes that are included in the gold standard.

The error sources for relation labeling are mostly the dependencies that involve possessives and the various types of objects (see Table 3) due to their differing valency. For instance, the relation det in su ‘his’/‘her’ ← det − coche ‘car’ and su ‘his’/‘her’ ← det − llamada ‘phone call’ have different correspondences in DSyntS: su ← ATTR − coche versus su ← I − llamada. That is, the DSyntS relation depends on the lexical properties of the governor. Once again, more training data is needed in order to classify better those cases.

(4) Post-processing: In the post-processing stage for Spanish, the following rules capture non-ambiguous correspondences between elements of the SSynt matrix I_s = N_s × N_s and DSyntS matrix I_d = N_d × N_d , with n_s ∈ N_s and n_d ∈ N_d , and n_s and n_d corresponding to each other (we do not list here identity correspondences such as between the number grammemes of n_s and n_d ):

• • if n_s is either dependent of analyt_pass or governor of aux_refl_pass relation, then the voice grammeme in n_d is PASS;

• • if n_s is dependent of analyt_progr, then the voice grammeme in n_d is PROGR;

• • if n_s is dependent of analyt_fut, then the tense grammeme in n_d is FUT;

• • if n_s is governor of aux_refl_lex, then add the particle -se as suffix of node label (word token) of d_d ;

• • if any of the children of n_s with the dependency label det is labeled by one of the tokens un, una, unos or unas, then the definiteness grammeme in n_d is INDEF; this grammeme is DEF for the tokens el, la, los and las;

• • if the n_s label is a finite verb and n_s does not govern a subject relation, then add to I_d the relation n_d − I → n′ _d , with n′ _d being a newly introduced node.