We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way.Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information.This approach leads to substantial performance improvements-19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting.As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task.

Paula Czarnowska, Sebastian Ruder, Edouard Grave, Ryan Cotterell, Ann Copestake. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

We propose sentence chunking as a way to reduce the time and memory costs of realization of long sentences.During chunking we divide the semantic representation of a sentence into smaller components which can be processed and recombined without loss of information.Our meaning representation of choice is Dependency Minimal Recursion Semantics (DMRS).We show that realizing chunks of a sentence and combining the results of such realizations increases the coverage for long sentences, significantly reduces the resources required and does not affect the quality of the realization.

Abstract This paper presents a classification-based approach to noun–noun compound interpretation within the statistical learning framework of kernel methods. In this framework, the primary modelling task is to define measures of similarity between data items, formalised as kernel functions. We consider the different sources of information that are useful for understanding compounds and proceed to define kernels that compute similarity between compounds in terms of these sources. In particular, these kernels implement intuitive notions of lexical and relational similarity and can be computed using distributional information extracted from text corpora. We report performance on classification experiments with three semantic relation inventories at different levels of granularity, demonstrating in each case that combining lexical and relational information sources is beneficial and gives better performance than either source taken alone. The data used in our experiments are taken from general English text, but our methods are also applicable to other domains and potentially to other languages where noun–noun compounding is frequent and productive.

BACKGROUND: Chemical named entities represent an important facet of biomedical text. RESULTS: We have developed a system to use character-based n-grams, Maximum Entropy Markov Models and rescoring to recognise chemical names and other such entities, and to make confidence estimates for the extracted entities. An adjustable threshold allows the system to be tuned to high precision or high recall. At a threshold set for balanced precision and recall, we were able to extract named entities at an F score of 80.7% from chemistry papers and 83.2% from PubMed abstracts. Furthermore, we were able to achieve 57.6% and 60.3% recall at 95% precision, and 58.9% and 49.1% precision at 90% recall. CONCLUSION: These results show that chemical named entities can be extracted with good performance, and that the properties of the extraction can be tuned to suit the demands of the task.

We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for attributes, which is only feasible for restricted domains. Our alternative works at the realisation level, relies on Word-Net synonym and antonym sets, and gives equivalent results on the examples cited in the literature and improved results for examples that prior approaches cannot handle. We believe that ours is also the first algorithm that allows for the incremental incorporation of relations. We present a novel corpus-evaluation using referring expressions from the Penn Wall Street Journal Treebank.

We develop a framework for formalizing semantic construction within grammars expressed in typed feature structure logics, including HPSG. The approach provides an alternative to the lambda calculus; it maintains much of the desirable flexibility of unification-based approaches to composition, while constraining the allowable operations in order to capture basic generalizations and improve maintainability.

We describe a formal framework for interpretation of words and compounds in a discourse context which integrates a symbolic lexicon/grammar, word-sense probabilities, and a pragmatic component. The approach is motivated by the need to handle productive word use. In this paper, we concentrate on compound nominals. We discuss the inadequacies of approaches which consider compund interpretation as either wholly lexico-grammatical or wholly pragmatic, and provide an alternative integrated account.