Papers by Mathias Niepert

8 papers
LRMM: Learning to Recommend with Missing Modalities (D18-1)

Copied to clipboard

Challenge: Existing methods for content-based recommendation with missing or corrupted modalities are lacking in learning multimodal models.
Approach: They propose a multimodal multimodal autoencoder that learns multimodal representations for complementing and imputing missing modalities.
Outcome: The proposed framework achieves state-of-the-art performance on rating prediction tasks and is more robust to previous methods in alleviating data-sparsity and the cold-start problem.
BenchIE: A Framework for Multi-Faceted Fact-Based Open Information Extraction Evaluation (2022.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for OIE are incomplete and do not include all acceptable variants of the same fact.
Approach: They introduce BenchIE: a benchmark and evaluation framework for comprehensive evaluation of OIE systems for English, Chinese, and German.
Outcome: The proposed framework is based on fact synsets, clusters, and standardized benchmarks.
Joint Multilingual Knowledge Graph Completion and Alignment (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing work on multilingual KG completion has focused on entity and relation alignments, but understanding of how it can aid multilingual alignments is limited.
Approach: They propose to combine two components that jointly accomplish KG completion and alignment.
Outcome: The proposed model outperforms existing competitive baselines on a public multilingual benchmark and achieves state-of-the-art results.
Attending to Future Tokens for Bidirectional Sequence Generation (D19-1)

Copied to clipboard

Challenge: Neural sequence generation is typically performed token-by-token and left-to-right.
Approach: They propose to use placeholder tokens to make the sequence generation process bidirectional by taking past and future tokens into consideration when generating the actual output token.
Outcome: The proposed approach outperforms baselines on two conversational tasks by a large margin.
Cross-Sentence N-ary Relation Extraction using Lower-Arity Universal Schemas (D19-1)

Copied to clipboard

Challenge: Existing approaches to extract n-ary relations from text are limited to binary relations.
Approach: They propose to learn relation representations of lower-arity facts from decomposing higher-arities . they conduct experiments with datasets for ternary relation extraction .
Outcome: The proposed method improves the performance of n-ary relation extraction methods compared to previous methods.
MILIE: Modular & Iterative Multilingual Open Information Extraction (2022.acl-long)

Copied to clipboard

Challenge: Current OpenIE systems extract all triple slots independently.
Approach: They propose a neural OpenIE system that extracts triple slots iteratively . they propose to use the system to extract easy slots and difficult ones .
Outcome: The proposed system outperforms SOTA systems on multiple languages ranging from Chinese to Arabic.
Learning Sequence Encoders for Temporal Knowledge Graph Completion (D18-1)

Copied to clipboard

Challenge: Existing work on link prediction in knowledge graphs has focused on static multi-relational data.
Approach: They propose to learn latent entity and relation type representations to incorporate temporal information into knowledge graphs.
Outcome: The proposed approach is robust to common challenges in real-world KGs.
AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark (2022.acl-demo)

Copied to clipboard

Challenge: Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner.
Approach: They propose an interactive annotation platform that facilitates annotating complete facts from input sentences.
Outcome: The proposed platform facilitates such challenging annotation tasks and supports creation of fact-oriented OIE evaluation benchmarks.

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