Papers by Martin Schmitt
Continuous Entailment Patterns for Lexical Inference in Context (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models can be used to perform lexical inference in context tasks with relatively small training data. |
| Approach: | They propose to combine a pretrained language model with textual patterns to improve performance in both zero-shot and few-shot settings. |
| Outcome: | The proposed method compares pre-trained models with textual patterns on two established benchmarks for lexical inference in context (LIiC) the results show that the proposed patterns improve performance on LIiC, setting a new state of the art. |
SherLIiC: A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference (P19-1)
Copied to clipboard
| Challenge: | We evaluate a large number of strong baselines on SherLIiC, ranging from semantic vector space models to state of the art neural models of natural language inference (NLI). |
| Approach: | They propose a testbed for lexical inference in context consisting of 3985 manually annotated inference rule candidates and a set of 960k unlabeled InfCands. |
| Outcome: | The proposed testbed is based on 3985 manually annotated inference rule candidates (InfCands) and 190k typed textual relations between Freebase entities extracted from the large entity-linked corpus ClueWeb09. |
An Unsupervised Joint System for Text Generation from Knowledge Graphs and Semantic Parsing (2020.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge graphs (KGs) vary greatly from one domain to another, resulting in a lack of domain-specific parallel graph-text data. |
| Approach: | They propose an unsupervised approach to graph-to-text generation and text-to graph knowledge extraction using WebNLG v2.1 and a new benchmark leveraging scene graphs from Visual Genome. |
| Outcome: | The proposed approach outperforms baselines on WebNLG v2.1 and a new benchmark leveraging scene graphs from Visual Genome. |
Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks (D18-1)
Copied to clipboard
| Challenge: | a new approach for aspect-based sentiment analysis is proposed . we compare the performance of the proposed approach with pipeline approaches . |
| Approach: | They propose a model for aspect-based sentiment analysis that uses a convolutional neural network and fasttext embeddings to combine the two approaches. |
| Outcome: | The proposed model outperforms pipeline approaches in aspects-based sentiment analysis. |
Language Models for Lexical Inference in Context (2021.eacl-main)
Copied to clipboard
| Challenge: | Lexical inference in context (LIiC) is a variant of the natural language inference task focused on lexical semantics. |
| Approach: | They propose three approaches based on pretrained language models for LIiC . they propose a few-shot NLI classifier and a relation induction approach based upon handcrafted patterns expressing the semantics of lexical inference. |
| Outcome: | The proposed approaches outperform the previous state of the art and show their potential for LIiC. |
Embedding Learning Through Multilingual Concept Induction (P18-1)
Copied to clipboard
| Challenge: | Existing methods for learning vector space representations of words are based on word-context information. |
| Approach: | They propose a method for estimating vector space representations of words by concept induction. |
| Outcome: | The proposed method performs better on crosslingual word similarity and sentiment analysis on a parallel corpus. |
A German Corpus for Fine-Grained Named Entity Recognition and Relation Extraction of Traffic and Industry Events (L18-1)
Copied to clipboard
Martin Schiersch, Veselina Mironova, Maximilian Schmitt, Philippe Thomas, Aleksandra Gabryszak, Leonhard Hennig
| Challenge: | Using text streams to extract events pertaining to specific companies, routes and routes remains a challenge. |
| Approach: | They describe a corpus of German-language documents annotated with fine-grained geo-entities and standard named entity types. |
| Outcome: | The proposed corpus consists of newswire texts, twitter messages, and traffic reports from radio stations, police and railway companies. |
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention (2020.coling-main)
Copied to clipboard
| Challenge: | SANs are an integral part of successful neural networks such as Transformer . training SAN on a task or pretraining them on language modeling requires large amounts of data and compute resources. |
| Approach: | They propose to modify SANs to enable faster learning, i.e., higher accuracies after fewer update steps. |
| Outcome: | The proposed modifications enable faster learning, i.e., higher accuracies after fewer update steps. |