Search Results for author:
Found 26 papers, 9 papers with code
Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment
Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems.
NTULM: Enriching Social Media Text Representations with Non-Textual Units
We refer to these annotations as Non-Textual Units (NTUs).
MiCRO: Multi-interest Candidate Retrieval Online
Providing personalized recommendations in an environment where items exhibit ephemerality and temporal relevancy (e. g. in social media) presents a few unique challenges: (1) inductively understanding ephemeral appeal for items in a setting where new items are created frequently, (2) adapting to trends within engagement patterns where items may undergo temporal shifts in relevance, (3) accurately modeling user preferences over this item space where users may express multiple interests.
TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter
Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network.
Non-Parametric Temporal Adaptation for Social Media Topic Classification
User-generated social media data is constantly changing as new trends influence online discussion and personal information is deleted due to privacy concerns.
kNN-Embed: Locally Smoothed Embedding Mixtures For Multi-interest Candidate Retrieval
To this end, we introduce kNN-Embed, a general approach to improving diversity in dense ANN-based retrieval.
Learning Stance Embeddings from Signed Social Graphs
We propose the Stance Embeddings Model(SEM), which jointly learns embeddings for each user and topic in signed social graphs with distinct edge types for each topic.
Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications
Sentence-level Quality estimation (QE) of machine translation is traditionally formulated as a regression task, and the performance of QE models is typically measured by Pearson correlation with human labels.
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation.
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.
Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data
The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages.
XLEnt: Mining a Large Cross-lingual Entity Dataset with Lexical-Semantic-Phonetic Word Alignment
Cross-lingual named-entity lexica are an important resource to multilingual NLP tasks such as machine translation and cross-lingual wikification.
Quality Estimation without Human-labeled Data
Quality estimation aims to measure the quality of translated content without access to a reference translation.
An Exploratory Study on Multilingual Quality Estimation
Predicting the quality of machine translation has traditionally been addressed with language-specific models, under the assumption that the quality label distribution or linguistic features exhibit traits that are not shared across languages.
Beyond English-Centric Multilingual Machine Translation
Existing work in translation demonstrated the potential of massively multilingual machine translation by training a single model able to translate between any pair of languages.
Massively Multilingual Document Alignment with Cross-lingual Sentence-Mover's Distance
Document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other.
Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approach
This proximity network captures the corpus-level co-occurence statistics for candidate event descriptors, event attributes, as well as their connections.
CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs
We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other.
Leveraging Pretrained Image Classifiers for Language-Based Segmentation
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining.
Facebook AI's WAT19 Myanmar-English Translation Task Submission
This paper describes Facebook AI's submission to the WAT 2019 Myanmar-English translation task.
Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings
However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures.
Constrained Sequence-to-sequence Semitic Root Extraction for Enriching Word Embeddings
In this paper, we tackle the problem of {``}root extraction{''} from words in the Semitic language family.
Entropy-Based Subword Mining with an Application to Word Embeddings
Recent literature has shown a wide variety of benefits to mapping traditional one-hot representations of words and phrases to lower-dimensional real-valued vectors known as word embeddings.
Integrating Local Context and Global Cohesiveness for Open Information Extraction
However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.
Scalable Topical Phrase Mining from Text Corpora
Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition.
