Papers by Huda Khayrallah

7 papers
SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training (2020.findings-emnlp)

Copied to clipboard

Challenge: Simulated Multiple Reference Training (SMRT) improves non-task-oriented dialog models by reducing the need for related-domain dialog data.
Approach: They apply Simulated Multiple Reference Training (SMRT) to chatbots to overcome sparse dialog data.
Outcome: The proposed model outperforms pretraining on human evaluation quality and lexical diversity without requiring related-domain dialog data.
HABLex: Human Annotated Bilingual Lexicons for Experiments in Machine Translation (D19-1)

Copied to clipboard

Challenge: Existing methods to incorporate bilingual lexicons into statistical machine translation are unclear how to do so in the neural framework.
Approach: They present a dataset to test methods for bilingual lexicon integration into neural machine translation using human generated alignments of words and phrases in three language pairs.
Outcome: The proposed method improves on baselines and improves training to address overfitting.
Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation (N19-1)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) performs poorly without large training corpora.
Approach: They propose a machine learning method that retains the majority of general-domain performance lost in continued training without degrading in-domain.
Outcome: The proposed method retains the majority of general-domain performance lost in continued training without degrading in-domain performances.
Simulated multiple reference training improves low-resource machine translation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing valid translations for a given sentence are limited by a single reference translation, causing data sparsity in low-resource settings.
Approach: They propose a method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a MT model and training it to predict the paraphraser’s distribution over possible tokens.
Outcome: The proposed method improves in low-resource settings and is complementary to back-translation.
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting (N19-1)

Copied to clipboard

Challenge: Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in machine translation or monolingual text rewriting tasks.
Approach: They propose a vectorized dynamic beam allocation algorithm which extends work in lexically-constrained decoding to work with batching.
Outcome: The proposed method improves on natural language inference, question answering and machine translation tasks by fivefold .
Measuring the ‘I don’t know’ Problem through the Lens of Gricean Quantity (2021.naacl-main)

Copied to clipboard

Challenge: Existing work on analyzing chatbots for generic, safe responses has not addressed the ‘I don’t know’ problem, but lack of analysis leaves it unclear if a method improves chatbot models by mitigating this problem, or another.
Approach: They propose to use Relative Utterance Quantity to diagnose the ‘I don’t know’ problem, in which a dialog system produces generic responses.
Outcome: The proposed method allows for the direct analysis of the ‘I don’t know’ problem, which has been addressed but not analyzed by prior work.
On-the-Fly Fusion of Large Language Models and Machine Translation (2024.findings-naacl)

Copied to clipboard

Challenge: a weaker-at-translation LLM can improve translations of a NMT model, compared to a strong dedicated model.
Approach: They propose to ensemble a neural machine translation model with a large language model, prompted on the same task and input.
Outcome: The proposed method can be combined with various techniques from LLM prompting, such as in context learning and translation context.

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