• Publications
  • Influence
Corpus-level Fine-grained Entity Typing Using Contextual Information
TLDR
This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class such as "food" or "artist" by proposing FIGMENT, a embedding-based and combines a global model that scores based on aggregated contextual information of an entity and a context model that first scores the individual occurrences of an entities and then aggregates the scores.
Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs
TLDR
ROPs, recurrent one-hop predictors, that predict entities at each step of mh-KB paths by using recurrent neural networks and vector representations of entities and relations are presented, showing state-of-the-art for two important multi-hop KG reasoning tasks: Knowledge Base Completion and Path Query Answering.
Probing for Semantic Classes: Diagnosing the Meaning Content of Word Embeddings
TLDR
A large dataset based on manual Wikipedia annotations and word senses, where word senses from different words are related by semantic classes is presented, and a classifier can accurately predict whether a word is single-sense or multi-sense, based only on its embedding.
Corpus-level Fine-grained Entity Typing
TLDR
This paper addresses the problem of corpus-level entity typing, i.e., inferring from a large corpus that an entity is a member of a class such as "food" or "artist" and proposes FIGMENT, an embedding- based and combines a global model that scores based on aggregated contextual information of an entities and a context model that first scores the individual occurrences of an entity and then aggregates the scores.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
Noise Mitigation for Neural Entity Typing and Relation Extraction
TLDR
This paper introduces multi-instance multi-label learning algorithms using neural network models, and applies them to fine-grained entity typing for the first time, and shows that probabilistic predictions are more robust than discrete predictions and that joint training of the two tasks performs best.
Multi-level Representations for Fine-Grained Typing of Knowledge Base Entities
TLDR
Methods for learning multi-level representations of entities on three complementary levels are presented, confirming experimentally that each level of representation contributes complementary information and a joint representation of all three levels improves the existing embedding based baseline for fine-grained entity typing by a large margin.
Intrinsic Subspace Evaluation of Word Embedding Representations
We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TLDR
Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.
Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing
TLDR
This work employs mul-itiview learning for increasing the accuracy and coverage of entity type information in KBs, and releases MVET, a large multiview — and, in particular, multilingual — entity typing dataset the authors created.
...
...