Papers by Gábor Recski
Better Together: Modern Methods Plus Traditional Thinking in NP Alignment (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that end-to-end systems are not structurally free. |
| Approach: | They propose to use dictionary- and word vector-based baselines to align NPs in the bitext . they argue that alignment of NP's in MT can be improved by using old-fashioned methods . |
| Outcome: | a new study shows that alignment of NPs in the bitext is relevant even in an end-to-end paradigm . the proposed system can be improved by bringing in old-fashioned methods, the authors argue . |
Improving Neural Conversational Models with Entropy-Based Data Filtering (P19-1)
Copied to clipboard
| Challenge: | Current neural network-based conversational models lack diversity and generate boring responses to open-ended utterances. |
| Approach: | They propose an unsupervised method of filtering dialog datasets by removing generic utterances from training data using an entropy-based approach that does not require human supervision. |
| Outcome: | The proposed method improves dialog quality as chatbots learn to output more diverse responses to open-ended utterances. |
BME-UW at SRST-2019: Surface realization with Interpreted Regular Tree Grammars (D19-63)
Copied to clipboard
| Challenge: | adaamko's system restores word order and inflection from a graph of typed, directed dependencies between lemmas. |
| Approach: | They propose a method that restores word order and inflection from a graph of typed, directed dependencies between lemmas. |
| Outcome: | The proposed system restores word order and inflection from a graph of typed, directed dependencies between lemmas. |
The Gutenberg Dialogue Dataset (2021.eacl-main)
Copied to clipboard
| Challenge: | Current open-domain dialogue datasets offer a trade-off between quality and size . we build a dataset of 14.8M utterances in English and smaller datasets in german, Dutch, Spanish, Portuguese, Italian, and Hungarian . |
| Approach: | They build a high-quality dialogue corpus of 14.8M utterances in English using public-domain books from Project Gutenberg. |
| Outcome: | The proposed datasets show that the extracted dialogues are more accurate and more accurate than the larger Opensubtitles dataset. |