In this paper, we examine the correlation between lexical semantics and the syntactic realization of the different components of a word’s meaning in natural language. More specifically, we will explore the effect that lexical factorization in verb semantics has on the suppression or expression of semantic features within the sentence. Factorization was a common analytic tool employed in early generative linguistic approaches to lexical decomposition, and continues to play a role in contemporary semantics, in various guises and modified forms. Building on the unpublished analysis of verbs of seeing in Joshi (1972), we argue here that the significance of lexical factorization is twofold: first, current models of verb meaning owe much of their insight to factor-based theories of meaning; secondly, the factorization properties of a lexical item appear to influence, both directly and indirectly, the possible syntactic expressibility of arguments and adjuncts in sentence composition. We argue that this information can be used to compute what we call the factor expression likelihood (FEL) associated with a verb in a sentence. This is the likelihood that the overt syntactic expression of a factor will cooccur with the verb. This has consequences for the compositional mechanisms responsible for computing the meaning of the sentence, as well as significance in the creation of computational models attempting to capture linguistic behavior over large corpora.

The PDTB Annotator is a tool for annotating and adjudicating discourse relations based on the annotation framework of the Penn Discourse TreeBank (PDTB). This demo describes the benefits of using the PDTB Annotator, gives an overview of the PDTB Framework and discusses the tool’s features, setup requirements and how it can also be used for adjudication.

We describe our experiments on evaluating recently proposed modifications to the discourse relation annotation scheme of the Penn Discourse Treebank (PDTB), in the context of annotating discourse relations in Hindi Discourse Relation Bank (HDRB). While the proposed modifications were driven by the desire to introduce greater conceptual clarity in the PDTB scheme and to facilitate better annotation quality, our findings indicate that overall, some of the changes render the annotation task much more difficult for the annotators, as also reflected in lower inter-annotator agreement for the relevant sub-tasks. Our study emphasizes the importance of best practices in annotation task design and guidelines, given that a major goal of an annotation effort should be to achieve maximally high agreement between annotators. Based on our study, we suggest modifications to the current version of the HDRB, to be incorporated in our future annotation work.

In this paper, we make a qualitative and quantitative analysis of discourse relations within the LUNA conversational spoken dialog corpus. In particular, we first describe the Penn Discourse Treebank (PDTB) and then we detail the adaptation of its annotation scheme to the LUNA corpus of Italian task-oriented dialogs in the domain of software/hardware assistance. We discuss similarities and differences between our approach and the PDTB paradigm and point out the peculiarities of spontaneous dialogs w.r.t. written text, which motivated some changes in the annotation strategy. In particular, we introduced the annotation of relations between non-contiguous arguments and we modified the sense hierarchy in order to take into account the important role of pragmatics in dialogs. In the final part of the paper, we present a comparison between the sense and connective frequency in a representative subset of the LUNA corpus and in the PDTB. Such analysis confirmed the differences between the two corpora and corroborates our choice to introduce dialog-specific adaptations.

We present an approach to automatically identifying the arguments of discourse connectives based on data from the Penn Discourse Treebank. Of the two arguments of connectives, called Arg1 and Arg2, we focus on Arg1, which has proven more challenging to identify. Our approach employs a sentence-based representation of arguments, and distinguishes ""intra-sentential connectives"", which take both their arguments in the same sentence, from ""inter-sentential connectives"", whose arguments are found in different sentences. The latter are further distinguished by paragraph position into ""ParaInit"" connectives, which appear in a paragraph-initial sentence, and ""ParaNonInit"" connectives, which appear elsewhere. The paper focusses on predicting Arg1 of Inter-sentential ParaNonInit connectives, presenting a set of scope-based filters that reduce the search space for Arg1 from all the previous sentences in the paragraph to a subset of them. For cases where these filters do not uniquely identify Arg1, coreference-based heuristics are employed. Our analysis shows an absolute 3% performance improvement over the high baseline of 83.3% for identifying Arg1 of Inter-sentential ParaNonInit connectives.

We present the second version of the Penn Discourse Treebank, PDTB-2.0, describing its lexically-grounded annotations of discourse relations and their two abstract object arguments over the 1 million word Wall Street Journal corpus. We describe all aspects of the annotation, including (a) the argument structure of discourse relations, (b) the sense annotation of the relations, and (c) the attribution of discourse relations and each of their arguments. We list the differences between PDTB-1.0 and PDTB-2.0. We present representative statistics for several aspects of the annotation in the corpus.

In syntax-directed translation, the source-language input is first parsed into a parse-tree, which is then recursively converted into a string in the target-language. We model this conversion by an extended tree-to-string transducer that has multi-level trees on the source-side, which gives our system more expressive power and flexibility. We also define a direct probability model and use a linear-time dynamic programming algorithm to search for the best derivation. The model is then extended to the general log-linear frame-work in order to incorporate other features like n-gram language models. We devise a simple-yet-effective algorithm to generate non-duplicate k-best translations for n-gram rescoring. Preliminary experiments on English-to-Chinese translation show a significant improvement in terms of translation quality compared to a state-of-the- art phrase-based system.

February 13-25, 1991

In this paper, we investigate the processing of the so-called ‘lexicalized’ grammar. In ‘lexicalized’ grammars (Schabes, Abeille and Joshi, 1988), each elementary structure is systema tically associated with a lexical ‘head’. These structures specify extended domains of locality (as compared to CFGs) over which constraints can be stated. The ‘grammar’ consists of a lexicon where each lexical item is associated with a finite number of structures for which that item is the ‘head’ . There are no separate grammar rules. There are, of course, ‘rules’ which tell us how these structures are combined. A general two-pass parsing strategy for ‘lexicalized’ grammars follows naturally. In the first stage, the parser selects a set of elementary structures associated with the lexical items in the input sentence, and in the second stage the sentence is parsed with respect to this set. We evaluate this strategy with respect to two characteristics. First, the amount of filtering on the entire grammar is evaluated: once the first pass is performed, the parser uses only a subset of the grammar. Second, we evaluate the use of non-local information: the structures selected during the first pass encode the morphological value (and therefore the position in the string) of their ‘head’; this enables the parser to use non-local in form ation to guide its search. We take Lexicalized Tree Adjoining Grammars as an in stance of lexicalized grammar. We illustrate the organization of the grammar. Then we show how a general Earley-type TAG parser (Schabes and Joshi, 1988) can take advantage of lexicalization. Empirical data show that the filtering of the grammar and the non-local in formation provided by the two-pass strategy improve the performance of the parser. We explain how constraints over the elementary structures expressed by unification equations can be parsed by a simple extension of the Earley-type TAG parser. Lexicalization guarantees termination of the algorithm without special devices such as restrictors.