Papers by Huda Khayrallah
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
J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, Benjamin Van Durme
| 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. |