no code implementations • NAACL (Wordplay) 2022 • Gregory Furman, Edan Toledo, Jonathan Shock, Jan Buys
Interactive Question Answering (IQA) requires an intelligent agent to interact with a dynamic environment in order to gather information necessary to answer a question.
1 code implementation • COLING 2022 • Sello Ralethe, Jan Buys
The generic overgeneralization effect refers to the inclination to accept false universal generalizations such as “all ducks lay eggs” or “all lions have manes” as true.
no code implementations • EMNLP (ACL) 2021 • Jaron Cohen, Roy Cohen, Edan Toledo, Jan Buys
We present RepGraph, an open source visualisation and analysis tool for meaning representation graphs.
no code implementations • 29 Mar 2024 • Francois Meyer, Jan Buys
Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations.
2 code implementations • 12 Mar 2024 • Francois Meyer, Jan Buys
In this paper we tackle data-to-text for isiXhosa, which is low-resource and agglutinative.
no code implementations • 31 Jan 2024 • Berta Franzluebbers, Donald Dunagan, Miloš Stanojević, Jan Buys, John T. Hale
Humans understand sentences word-by-word, in the order that they hear them.
1 code implementation • 11 May 2023 • Francois Meyer, Jan Buys
We propose a departure from this paradigm, called subword segmental machine translation (SSMT).
no code implementations • 21 Oct 2022 • Khalid N. Elmadani, Francois Meyer, Jan Buys
The paper describes the University of Cape Town's submission to the constrained track of the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages.
1 code implementation • 12 Oct 2022 • Francois Meyer, Jan Buys
We also train our model as a word-level sequence model, resulting in an unsupervised morphological segmenter that outperforms existing methods by a large margin for all 4 languages.
1 code implementation • 1 Apr 2021 • Stuart Mesham, Luc Hayward, Jared Shapiro, Jan Buys
Language models are the foundation of current neural network-based models for natural language understanding and generation.
1 code implementation • 1 Apr 2021 • Tumi Moeng, Sheldon Reay, Aaron Daniels, Jan Buys
In this paper, we investigate supervised and unsupervised models for two variants of morphological segmentation: canonical and surface segmentation.
no code implementations • IJCNLP 2019 • Peter West, Ari Holtzman, Jan Buys, Yejin Choi
In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a conditional language modelling objective: given a sentence, our approach seeks a compressed sentence that can best predict the next sentence.
no code implementations • EACL 2021 • Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi
We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
1 code implementation • NAACL 2019 • Yonatan Bisk, Jan Buys, Karl Pichotta, Yejin Choi
Understanding procedural language requires reasoning about both hierarchical and temporal relations between events.
1 code implementation • NAACL 2019 • Valerie Hajdik, Jan Buys, Michael W. Goodman, Emily M. Bender
We propose neural models to generate high-quality text from structured representations based on Minimal Recursion Semantics (MRS).
16 code implementations • ICLR 2020 • Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, Yejin Choi
Despite considerable advancements with deep neural language models, the enigma of neural text degeneration persists when these models are tested as text generators.
no code implementations • NAACL 2018 • Jan Buys, Phil Blunsom
We present neural syntactic generative models with exact marginalization that support both dependency parsing and language modeling.
2 code implementations • ACL 2018 • Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, David Golub, Yejin Choi
Recurrent Neural Networks (RNNs) are powerful autoregressive sequence models, but when used to generate natural language their output tends to be overly generic, repetitive, and self-contradictory.
no code implementations • ICLR 2018 • Ari Holtzman, Jan Buys, Maxwell Forbes, Antoine Bosselut, Yejin Choi
Human evaluation demonstrates that text generated by the resulting generator is preferred over that of baselines by a large margin and significantly enhances the overall coherence, style, and information content of the generated text.
no code implementations • SEMEVAL 2017 • Jan Buys, Phil Blunsom
We present a neural encoder-decoder AMR parser that extends an attention-based model by predicting the alignment between graph nodes and sentence tokens explicitly with a pointer mechanism.
Ranked #27 on AMR Parsing on LDC2017T10
1 code implementation • ACL 2017 • Jan Buys, Phil Blunsom
Parsing sentences to linguistically-expressive semantic representations is a key goal of Natural Language Processing.
no code implementations • EMNLP 2016 • Lei Yu, Jan Buys, Phil Blunsom
We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read.
no code implementations • ACL 2016 • Jan Buys, Jan A. Botha
We propose a tagging model using Wsabie, a discriminative embedding-based model with rank-based learning.
no code implementations • WS 2015 • Jan Buys, Phil Blunsom
We propose a simple, scalable, fully generative model for transition-based dependency parsing with high accuracy.