Papers by Gábor Recski

4 papers
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.

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