Papers by William Lane

6 papers
Bootstrapping Techniques for Polysynthetic Morphological Analysis (2020.acl-main)

Copied to clipboard

Challenge: Polysynthetic languages have exceptionally large and sparse vocabularies due to the number of morpheme slots and combinations in a word.
Approach: They propose linguistically-informed approaches for bootstrapping a neural morphological analyzer . they use a finite state transducer to train an encoder-decoder model .
Outcome: The proposed method improves on a polysynthetic language's model by "hallucinating" missing linguistic structure and resampling from a Zipf distribution to simulate a more natural distribution of morphemes.
Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG induction (D18-1)

Copied to clipboard

Challenge: Recent attempts to improve grammar induction systems by bounding complexity of the model have not been compared against unbounded induction models.
Approach: They propose to use a Bayesian induction inducer to limit the search space of the model and then sample trees with or without bounding.
Outcome: The proposed model produces trees more accurately than or competitively with state-of-the-art constituency grammar induction models.
Local Word Discovery for Interactive Transcription (2021.emnlp-main)

Copied to clipboard

Challenge: a new computational task supports the construction of high quality texts and lexicons for low resource languages.
Approach: They propose a computational task which is tuned to the available knowledge and interests in an Indigenous community.
Outcome: The proposed method achieves a transcription density gain of 17% in a morphologically complex language . the proposed grammar includes a description of the phonology and morphosyntax .
Interactive Word Completion for Plains Cree (2022.acl-long)

Copied to clipboard

Challenge: a tool that helps users incrementally build complex words is being developed in morphologically complex languages.
Approach: They propose a finite state approach which maps prefixes in a language to completions up to the next morpheme boundary for incremental building of complex words.
Outcome: The proposed approach shows portability to a larger, more complete morphological transducer.
Interactive Word Completion for Morphologically Complex Languages (2020.coling-main)

Copied to clipboard

Challenge: morphologically complex languages have multiple morph slots with large or unbounded sets of fillers.
Approach: They propose a method for morphologically-aware text input in Kunwinjku . they modify an existing finite state recognizer to map input morph prefixes to morph completions .
Outcome: The proposed method is portable to Turkish and shows that it can be used in other languages.
Unsupervised Learning of PCFGs with Normalizing Flow (P19-1)

Copied to clipboard

Challenge: Existing induction models unable to incorporate semantics and morphology into induction . current models lack a robust model for generating morphologically rich sentences .
Approach: They propose a PCFG inducer which uses context embeddings to generalize over rare, morphologically rich forms.
Outcome: The proposed model produces grammars with state-of-the-art accuracy on a variety of languages.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations