arXiv subjects

Michael Strube

Publications and source records attributed to Michael Strube.

35 records · Page 2Linked to original sources

arXiv2019

Using Automatically Extracted Minimum Spans to Disentangle Coreference Evaluation from Boundary Detection

The common practice in coreference resolution is to identify and evaluate the maximum span of mentions. The use of maximum spans tangles coreference evaluation with the challenges of mention boundary detection like prepositional phrase attachment. To address this problem, minimum spans are manually annotated in smaller corpora. However, this additional annotation is costly and therefore, this solution does not scale to large corpora. In this paper, we propose the MINA algorithm for automatically extracting minimum spans to benefit from minimum span evaluation in all corpora. We show that the extracted minimum spans by MINA are consistent with those that are manually annotated by experts. Our experiments show that using minimum spans is in particular important in cross-dataset coreference evaluation, in which detected mention boundaries are noisier due to domain shift. We will integrate MINA into https://github.com/ns-moosavi/coval for reporting standard coreference scores based on both maximum and automatically detected minimum spans.

cs.CL↗

arXiv2019

Fine-Grained Entity Typing in Hyperbolic Space

How can we represent hierarchical information present in large type inventories for entity typing? We study the ability of hyperbolic embeddings to capture hierarchical relations between mentions in context and their target types in a shared vector space. We evaluate on two datasets and investigate two different techniques for creating a large hierarchical entity type inventory: from an expert-generated ontology and by automatically mining type co-occurrences. We find that the hyperbolic model yields improvements over its Euclidean counterpart in some, but not all cases. Our analysis suggests that the adequacy of this geometry depends on the granularity of the type inventory and the way hierarchical relations are inferred.

cs.CL↗

arXiv2019

Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation

Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of pretrained embeddings, the distinct lack of systematic evaluations makes it difficult for practitioners to choose between them. In this work, we conduct an extensive evaluation comparing non-contextual subword embeddings, namely FastText and BPEmb, and a contextual representation method, namely BERT, on multilingual named entity recognition and part-of-speech tagging. We find that overall, a combination of BERT, BPEmb, and character representations works best across languages and tasks. A more detailed analysis reveals different strengths and weaknesses: Multilingual BERT performs well in medium- to high-resource languages, but is outperformed by non-contextual subword embeddings in a low-resource setting.

cs.CL↗

arXiv2018

Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers

Coreference resolution is an intermediate step for text understanding. It is used in tasks and domains for which we do not necessarily have coreference annotated corpora. Therefore, generalization is of special importance for coreference resolution. However, while recent coreference resolvers have notable improvements on the CoNLL dataset, they struggle to generalize properly to new domains or datasets. In this paper, we investigate the role of linguistic features in building more generalizable coreference resolvers. We show that generalization improves only slightly by merely using a set of additional linguistic features. However, employing features and subsets of their values that are informative for coreference resolution, considerably improves generalization. Thanks to better generalization, our system achieves state-of-the-art results in out-of-domain evaluations, e.g., on WikiCoref, our system, which is trained on CoNLL, achieves on-par performance with a system designed for this dataset.

cs.CL↗

arXiv2018

Transparent, Efficient, and Robust Word Embedding Access with WOMBAT

We present WOMBAT, a Python tool which supports NLP practitioners in accessing word embeddings from code. WOMBAT addresses common research problems, including unified access, scaling, and robust and reproducible preprocessing. Code that uses WOMBAT for accessing word embeddings is not only cleaner, more readable, and easier to reuse, but also much more efficient than code using standard in-memory methods: a Python script using WOMBAT for evaluating seven large word embedding collections (8.7M embedding vectors in total) on a simple SemEval sentence similarity task involving 250 raw sentence pairs completes in under ten seconds end-to-end on a standard notebook computer.

cs.CL↗

arXiv2017

BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages

We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as testbed, BPEmb performs competitively, and for some languages bet- ter than alternative subword approaches, while requiring vastly fewer resources and no tokenization. BPEmb is available at https://github.com/bheinzerling/bpemb

cs.CL↗

arXiv2017

Revisiting Selectional Preferences for Coreference Resolution

Selectional preferences have long been claimed to be essential for coreference resolution. However, they are mainly modeled only implicitly by current coreference resolvers. We propose a dependency-based embedding model of selectional preferences which allows fine-grained compatibility judgments with high coverage. We show that the incorporation of our model improves coreference resolution performance on the CoNLL dataset, matching the state-of-the-art results of a more complex system. However, it comes with a cost that makes it debatable how worthwhile such improvements are.

cs.CL↗

arXiv2017

Lexical Features in Coreference Resolution: To be Used With Caution

Lexical features are a major source of information in state-of-the-art coreference resolvers. Lexical features implicitly model some of the linguistic phenomena at a fine granularity level. They are especially useful for representing the context of mentions. In this paper we investigate a drawback of using many lexical features in state-of-the-art coreference resolvers. We show that if coreference resolvers mainly rely on lexical features, they can hardly generalize to unseen domains. Furthermore, we show that the current coreference resolution evaluation is clearly flawed by only evaluating on a specific split of a specific dataset in which there is a notable overlap between the training, development and test sets.

cs.CL↗

arXiv2017

Use Generalized Representations, But Do Not Forget Surface Features

Only a year ago, all state-of-the-art coreference resolvers were using an extensive amount of surface features. Recently, there was a paradigm shift towards using word embeddings and deep neural networks, where the use of surface features is very limited. In this paper, we show that a simple SVM model with surface features outperforms more complex neural models for detecting anaphoric mentions. Our analysis suggests that using generalized representations and surface features have different strength that should be both taken into account for improving coreference resolution.

cs.CL↗

arXiv1998

Never Look Back: An Alternative to Centering

I propose a model for determining the hearer's attentional state which depends solely on a list of salient discourse entities (S-list). The ordering among the elements of the S-list covers also the function of the backward-looking center in the centering model. The ranking criteria for the S-list are based on the distinction between hearer-old and hearer-new discourse entities and incorporate preferences for inter- and intra-sentential anaphora. The model is the basis for an algorithm which operates incrementally, word by word.

cmp-lg↗

arXiv1997

Centering in-the-large: Computing referential discourse segments

We specify an algorithm that builds up a hierarchy of referential discourse segments from local centering data. The spatial extension and nesting of these discourse segments constrain the reachability of potential antecedents of an anaphoric expression beyond the local level of adjacent center pairs. Thus, the centering model is scaled up to the level of the global referential structure of discourse. An empirical evaluation of the algorithm is supplied.

cmp-lg↗

arXiv1996

Incremental Centering and Center Ambiguity

In this paper, we present a model of anaphor resolution within the framework of the centering model. The consideration of an incremental processing mode introduces the need to manage structural ambiguity at the center level. Hence, the centering framework is further refined to account for local and global parsing ambiguities which propagate up to the level of center representations, yielding moderately adapted data structures for the centering algorithm.

cmp-lg↗

arXiv1996

A Conceptual Reasoning Approach to Textual Ellipsis

We present a hybrid text understanding methodology for the resolution of textual ellipsis. It integrates conceptual criteria (based on the well-formedness and conceptual strength of role chains in a terminological knowledge base) and functional constraints reflecting the utterances' information structure (based on the distinction between context-bound and unbound discourse elements). The methodological framework for text ellipsis resolution is the centering model that has been adapted to these constraints.

cmp-lg↗

arXiv1996

Functional Centering

Based on empirical evidence from a free word order language (German) we propose a fundamental revision of the principles guiding the ordering of discourse entities in the forward-looking centers within the centering model. We claim that grammatical role criteria should be replaced by indicators of the functional information structure of the utterances, i.e., the distinction between context-bound and unbound discourse elements. This claim is backed up by an empirical evaluation of functional centering.

cmp-lg↗

arXiv1996

Processing Complex Sentences in the Centering Framework

We extend the centering model for the resolution of intra-sentential anaphora and specify how to handle complex sentences. An empirical evaluation indicates that the functional information structure guides the search for an antecedent within the sentence.

cmp-lg↗

arXiv1995

ParseTalk about Textual Ellipsis

A hybrid methodology for the resolution of text-level ellipsis is presented in this paper. It incorporates conceptual proximity criteria applied to ontologically well-engineered domain knowledge bases and an approach to centering based on functional topic/comment patterns. We state text grammatical predicates for ellipsis and then turn to the procedural aspects of their evaluation within the framework of an actor-based implementation of a lexically distributed parser.

cmp-lg↗

arXiv1995

ParseTalk about Sentence- and Text-Level Anaphora

We provide a unified account of sentence-level and text-level anaphora within the framework of a dependency-based grammar model. Criteria for anaphora resolution within sentence boundaries rephrase major concepts from GB's binding theory, while those for text-level anaphora incorporate an adapted version of a Grosz-Sidner-style focus model.

cmp-lg↗