Search Results for author: Benoît Crabbé

Found 6 papers, 3 papers with code

The impact of lexical and grammatical processing on generating code from natural language

1 code implementation Findings (ACL) 2022 Nathanaël Beau, Benoît Crabbé

Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mechanisms.

Code Generation Code Translation +1

Can RNNs learn Recursive Nested Subject-Verb Agreements?

no code implementations6 Jan 2021 Yair Lakretz, Théo Desbordes, Jean-Rémi King, Benoît Crabbé, Maxime Oquab, Stanislas Dehaene

Finally, probing the internal states of the model during the processing of sentences with nested tree structures, we found a complex encoding of grammatical agreement information (e. g. grammatical number), in which all the information for multiple words nouns was carried by a single unit.

Unlexicalized Transition-based Discontinuous Constituency Parsing

1 code implementation TACL 2019 Maximin Coavoux, Benoît Crabbé, Shay B. Cohen

Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities.

Constituency Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.