Lonneke van der Plas

Finding Synonyms Using Automatic Word Alignment and Measures of Distributional Similarity

There have been many proposals to extract semantically related words using measures of distributional similarity, but these typically are not able to distinguish between synonyms and other types of semantically related words such as antonyms, (co)hyponyms and hypernyms. We present a method based on automatic word alignment of parallel corpora consisting of documents translated into multiple languages and compare our method with a monolingual syntax-based method. The approach that uses aligned multilingual data to extract synonyms shows much higher precision and recall scores for the task of synonym extraction than the monolingual syntax-based approach.

Question answering for dutch using dependency relations

Joost is a question answering system for Dutch which makes extensive use of dependency relations. It answers questions either by table look-up, or by searching for answers in paragraphs returned by IR. Syntactic similarity is used to identify and rank potential answers. Tables were constructed by mining the CLEF corpus, which has been syntactically analyzed in full.

Abstraction and Generalisation in Semantic Role Labels: PropBank, VerbNet or both?

Semantic role labels are the representation of the grammatically relevant aspects of a sentence meaning. Capturing the nature and the number of semantic roles in a sentence is therefore fundamental to correctly describing the interface between grammar and meaning. In this paper, we compare two annotation schemes, Prop-Bank and VerbNet, in a task-independent, general way, analysing how well they fare in capturing the linguistic generalisations that are known to hold for semantic role labels, and consequently how well they grammaticalise aspects of meaning. We show that VerbNet is more verb-specific and better able to generalise to new semantic role instances, while PropBank better captures some of the structural constraints among roles. We conclude that these two resources should be used together, as they are complementary.

Using Lexico-Semantic Information for Query Expansion in Passage Retrieval for Question Answering

In this paper we investigate the use of several types of lexico-semantic information for query expansion in the passage retrieval component of our QA system. We have used four corpus-based methods to acquire semantically related words, and we have used one hand-built resource. We evaluate our techniques on the Dutch CLEF QA track. In our experiments expansions that try to bridge the terminological gap between question and document collection do not result in any improvements. However, expansions bridging the knowledge gap show modest improvements.

Question Answering with Joost at CLEF 2007

We describe our system for the monolingual Dutch and multilingual English to Dutch QA tasks. We describe the preprocessing of Wikipedia, inclusion of query expansion in IR, anaphora resolution in follow-up questions, and a question classification module for the multilingual task. Our best runs achieved 25.5% accuracy for the Dutch monolingual task, and 13.5% accuracy for the multilingual task.

Domain Adaptation with Artificial Data for Semantic Parsing of Speech

We adapt a semantic role parser to the domain of goal-directed speech by creating an artificial treebank from an existing text tree-bank. We use a three-component model that includes distributional models from both target and source domains. We show that we improve the parsers performance on utterances collected from human-machine dialogues by training on the artificially created data without loss of performance on the text treebank.

Multiword Expression Processing: A Survey

Multiword expressions (MWEs) are a class of linguistic forms spanning conventional word boundaries that are both idiosyncratic and pervasive across different languages. The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs. The issue of MWE handling is crucial for NLP applications, where it raises a number of challenges. The emergence of solutions in the absence of guiding principles motivates this survey, whose aim is not only to provide a focused review of MWE processing, but also to clarify the nature of interactions between MWE processing and downstream applications. We propose a conceptual framework within which challenges and research contributions can be positioned. It offers a shared understanding of what is meant by “MWE processing,” distinguishing the subtasks of MWE discovery and identification. It also elucidates the interactions between MWE processing and two use cases: Parsing and machine translation. Many of the approaches in the literature can be differentiated according to how MWE processing is timed with respect to underlying use cases. We discuss how such orchestration choices affect the scope of MWE-aware systems. For each of the two MWE processing subtasks and for each of the two use cases, we conclude on open issues and research perspectives.

Automatic acquisition of lexico-semantic knowledge for question answering

Lexico-semantic knowledge is becoming increasingly important within the area of natural language processing, especially for applications, such as Word Sense Disambiguation, Information Extraction and Question Answering (QA). Although the coverage of handmade resources, such as WordNet (Fellbaum, 1998), in general is impressive, coverage problems still exist for those applications involving specific domains or languages other than English. We are interested in using lexico-semantic knowledge in an open-domain question answering system for Dutch. Obtaining such knowledge from existing resources is possible, but only to a certain extent. The most important resource for our research is the Dutch portion of EuroWord-Net (Vossen, 1998), however its size is only half of that of the English WordNet. Therefore, many of the lexical items used in the QA task of the Cross Language Evaluation Forum (CLEF 1) for Dutch cannot be found in EuroWordNet. In addition, information regarding the classes to which named entities belong, e.g. Narvik IS-A harbour, has been shown to be useful for QA, but such information is typically absent from hand-built resources. For these reasons, we are interested in investigating methods which acquire lexico-semantic knowledge automatically from text corpora.

Predicting Pronouns across Languages with Continuous Word Spaces

Predicting pronouns across languages from a language with less variation to one with much more is a hard task that requires many different types of information, such as morpho-syntactic information as well as lexical semantics and coreference. We assumed that continuous word spaces fed into a multi-layer perceptron enriched with morphological tags and coreference resolution would be able to capture many of the linguistic regularities we found. Our results show that the model captures most of the linguistic generalisations. Its macro-averaged F-score is among the top-3 systems submitted to the DiscoMT shared task reaching 56.5%.

Using syntactic knowledge for QA

We describe the system of the University of Groningen for the monolingual Dutch and multilingual English to Dutch QA tasks. First, we give a brief outline of the architecture of our QA-system, which makes heavy use of syntactic information. Next, we describe the modules that were improved or developed especially for the CLEF tasks, among others incorporation of syntactic knowledge in IR, incorporation of lexical equivalences and coreference resolution, and a baseline multilingual (English to Dutch) QA system, which uses a combination of Systran and Wikipedia (for term recognition and translation) for question translation. For non-list questions, 31% (20%) of the highest ranked answers returned by the monolingual (multilingual) system were correct.