Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings

By Annette Rios Gonzales, Laura Mascarell, Rico Sennrich. 2017

133 citations recorded by the source corpus.

Word sense disambiguation is necessary in translation because different word senses often have different translations. Neural machine translation models learn different senses of words as part of an end-to-end translation task, and their capability to perform word sense disambiguation has so far not been quantified. We exploit the fact that neural translation models can score arbitrary translations to design a novel cross-lingual word sense disambiguation task that is tailored towards evaluating neural machine translation models. We present a test set of 7,200 lexical ambiguities for German → English, and 6,700 for German → French, and report baseline results. With 70% of lexical ambiguities correctly disambiguated, we find that word sense disambiguation remains a challenging problem for neural machine translation, especially for rare word senses. To improve word sense disambiguation in neural machine translation, we experiment with two methods to integrate sense embeddings. In a first approach we pass sense embeddings as additional input to the neural machine translation system. For the second experiment, we extract lexical chains based on sense embeddings from the document and integrate this information into the NMT model. While a baseline NMT system disambiguates frequent word senses quite reliably, the annotation with both sense labels and lexical chains improves the neural models’ performance on rare word senses.

Subfields: Artificial Intelligence, Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Machine Translation

Citations in the corpus

Analysis Methods in Neural Language Processing: A Survey (2018, methodology): “This framework was extended to evaluate other properties, but often requiring more sophisticated generation methods like using morphological analyzers/generators (Burlot and Yvon, 2017) or more manual involvement in generation (Bawden et al., 2018) or veriﬁcation (Rios Gonzales et al., 2017).”
Why Self-Attention? A Targeted Evaluation of Neural Machine Translation Architectures (2018, background): “1 million sentence pairs from Europarl (v7) (Tiedemann, 2012)4 and News Commentary (v11) cleaned by Rios et al. (2017)5 as our training set.”
Evaluating Discourse Phenomena in Neural Machine Translation (2017, methodology): “This method was used by Sennrich (2017) to assess the grammaticality of character-level NMT and again by Rios Gonzales et al. (2017) in a large-scale setting for lexical disambiguation for English-German.”
On internal language representations in deep learning: an analysis of machine translation and speech recognition (2018, methodology): “On the analysis side, recent work has considered how word senses are captured in neural machine translation by evaluating systems on contrastive pairs [285], or by visualizing representations and measuring their disambiguation quality [228].”
BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation (2021, background): “…discourse-level phenomena have been proposed (Hardmeier et al., 2015; Guillou and Hardmeier, 2016; Burchardt et al., 2017; Isabelle et al., 2017; Rios Gonzales et al., 2017; Müller et al., 2018; Bawden et al., 2018; Voita et al., 2019; Guillou and Hardmeier, 2018, inter alia ) for…”
Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments (2018, background): “Coherence on the other hand, is important for producing consistent and coherent translations throughout a document, especially for domain-speciﬁc terminology (Carpuat, 2009; Ture et al., 2012; Gonzales et al., 2017) and it is helpful to properly disambiguate polysemous words.”