Morphological Reinflection via Discriminative String Transduction

Nicolai, Garrett; Hauer, Bradley; Arnaud, Adam St; Kondrak, Grzegorz

doi:10.18653/v1/w16-2005

Cited by 15 publications

(19 citation statements)

References 6 publications

(7 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the SIGMORPHON 2016 and the CoNLL-SIGMORPHON 2017 shared tasks (Cotterell et al, , 2017, multiple MRI systems were developed, e.g., (Nicolai et al, 2016;Taji et al, 2016;Kann and Schütze, 2016;Östling, 2016;Makarov et al, 2017). Encoder-decoder neural networks (Cho et al, 2014a; performed best, such that we extend them in this work.…”

Section: Related Workmentioning

confidence: 93%

“…This task was addressed through several approaches, including align and transduce (Alegria and Etxeberria, 2016;Nicolai et al, 2016;Liu and Mao, 2016); recurrent neural networks (Kann and Schütze, 2016;Östling, 2016); and, linguisticinspired heuristics approaches (Taji et al, 2016;Sorokin, 2016). Overall, recurrent neural networks approaches performed better, being (Kann and Schütze, 2016) the best performing system in the shared task, obtaining around 98%.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Proceedings of the First Workshop on Subword and Character Level Models in NLP

2017

View full text Add to dashboard Cite

IntroductionTraditional NLP starts with a hand-engineered layer of representation, the level of tokens or words. A tokenization component first breaks up the text into units using manually designed rules. Tokens are then processed by components such as word segmentation, morphological analysis and multiword recognition. The heterogeneity of these components makes it hard to create integrated models of both structure within tokens (e.g., morphology) and structure across multiple tokens (e.g., multi-word expressions). This approach can perform poorly (i) for morphologically rich languages, (ii) for noisy text, (iii) for languages in which the recognition of words is difficult and (iv) for adaptation to new domains; and (v) it can impede the optimization of preprocessing in end-to-end learning.The workshop provides a forum for discussing recent advances as well as future directions on sub-word and character-level natural language processing and representation learning that address these problems.We received 37 submissions, out of which we accepted 24 as papers and 4 as extended abstracts. AbstractMost of neural language models use different kinds of embeddings for word prediction. While word embeddings can be associated to each word in the vocabulary or derived from characters as well as factored morphological decomposition, these word representations are mainly used to parametrize the input, i.e. the context of prediction. This work investigates the effect of using subword units (character and factored morphological decomposition) to build output representations for neural language modeling. We present a case study on Czech, a morphologically-rich language, experimenting with different input and output representations. When working with the full training vocabulary, despite unstable training, our experiments show that augmenting the output word representations with character-based embeddings can significantly improve the performance of the model. Moreover, reducing the size of the output look-up table, to let the character-based embeddings represent rare words, brings further improvement. IntroductionMost of neural language models, such as n-gram models (Bengio et al., 2003) are word based and rely on the definition of a finite vocabulary V. Therefore, a look-up table maps each wordw ∈ V to a vector of real features, and is stored in a matrix. While this approach yields significant improvement for a variety of tasks and languages, see for instance (Schwenk, 2007) in speech recognition and (Le et al., 2012; Devlin et al., 2014; in machine translation, it induces several limitations.For morphologically-rich languages, like Czech or German, the lexical coverage is still an important issue, since there is a combinatorial explosion of word forms, most of which are hardly observed on training data. On the one hand, growing the look-up table is not a solution, since it would increase the number of parameters without having enough training examples for a proper estimation. On the other hand, rare words can be replaced...

show abstract

Section: Related Workmentioning

confidence: 93%

Section: Related Workmentioning

confidence: 99%

Proceedings of the First Workshop on Subword and Character Level Models in NLP

2017

View full text Add to dashboard Cite

show abstract

“…This task was addressed through several approaches, including align and transduce (Alegria and Etxeberria, 2016;Nicolai et al, 2016;Liu and Mao, 2016); recurrent neural networks (Kann and Schütze, 2016;Aharoni et al, 2016;Ostling, 2016); and linguistic-inspired heuristics approaches (Taji et al, 2016;Sorokin, 2016). Overall, recurrent neural networks approaches performed better, being (Kann and Schütze, 2016) the best performing system in the shared task, obtaining around 98%.…”

Section: Related Workmentioning

confidence: 99%

Improving the Naturalness and Expressivity of Language Generation for Spanish

Barros¹,

Gkatzia²,

Lloret³

2017

Proceedings of the 10th International Conference on Natural Language Generation

View full text Add to dashboard Cite

We present a flexible Natural Language Generation approach for Spanish, focused on the surface realisation stage, which integrates an inflection module in order to improve the naturalness and expressivity of the generated language. This inflection module inflects the verbs using an ensemble of trainable algorithms whereas the other types of words (e.g. nouns, determiners, etc) are inflected using hand-crafted rules. We show that our approach achieves 2% higher accuracy than two stateof-art inflection generation approaches. Furthermore, our proposed approach also predicts an extra feature: the inflection of the imperative mood, which was not taken into account by previous work. We also present a user evaluation, where we demonstrate that the proposed method significantly improves the perceived naturalness of the generated language.

show abstract

“…In the small training data scenario, it is not practical to treat tag sequences as atomic units, as we did in Nicolai et al (2016), because many tag sequences may be represented by only a single training instance, or not at all. We follow in separating each tag sequence into its component subtags, in order to share information across inflection slots.…”

Section: Tag Splittingmentioning

confidence: 99%

“…For example, Liu and Mao (2016) and King (2016) use Conditional Random Fields (CRF) and Alegria and Etxeberria (2016) and Nicolai et al (2016) employ different phoneme-tographeme translation systems. Other approaches include learning a morphological analyzer from training data and applying it to reinflect test examples (Taji et al, 2016) and extracting morphological paradigms from the training data which are then applied on test words Sorokin, 2016).…”

Section: Related Workmentioning

confidence: 99%

Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection

Hulden¹

2017

View full text Add to dashboard Cite

Morphological Reinflection via Discriminative String Transduction

Abstract: We describe our approach and experiments in the context of the SIGMOR-PHON 2016 Shared Task on Morphological Reinflection. The results show that the methods of Nicolai et al. (2015) perform well on typologically diverse languages. We also discuss language-specific heuristics and errors.

Cited by 15 publications

References 6 publications

Proceedings of the First Workshop on Subword and Character Level Models in NLP

Proceedings of the First Workshop on Subword and Character Level Models in NLP

Improving the Naturalness and Expressivity of Language Generation for Spanish

Proceedings of the CoNLL SIGMORPHON 2017 Shared Task: Universal Morphological Reinflection

Contact Info

Product

Resources

About