Search Results for author: Alexander Koller

Found 29 papers, 13 papers with code

MC-Saar-Instruct: a Platform for Minecraft Instruction Giving Agents

no code implementations SIGDIAL (ACL) 2020 Arne Köhn, Julia Wichlacz, Christine Schäfer, Álvaro Torralba, Joerg Hoffmann, Alexander Koller

We present a comprehensive platform to run human-computer experiments where an agent instructs a human in Minecraft, a 3D blocksworld environment.

Compositional generalization with a broad-coverage semantic parser

1 code implementation *SEM (NAACL) 2022 Pia Weißenhorn, Lucia Donatelli, Alexander Koller

We show how the AM parser, a compositional semantic parser (Groschwitz et al., 2018) can solve compositional generalization on the COGS dataset.

Aligning Actions Across Recipe Graphs

1 code implementation EMNLP 2021 Lucia Donatelli, Theresa Schmidt, Debanjali Biswas, Arne Köhn, Fangzhou Zhai, Alexander Koller

Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding.


Predicting Coreference in Abstract Meaning Representations

no code implementations COLING (CRAC) 2020 Tatiana Anikina, Alexander Koller, Michael Roth

This work addresses coreference resolution in Abstract Meaning Representation (AMR) graphs, a popular formalism for semantic parsing.

coreference-resolution Semantic Parsing

Simple and effective data augmentation for compositional generalization

no code implementations18 Jan 2024 Yuekun Yao, Alexander Koller

Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models.

Data Augmentation

AutoPlanBench: Automatically generating benchmarks for LLM planners from PDDL

1 code implementation16 Nov 2023 Katharina Stein, Daniel Fišer, Jörg Hoffmann, Alexander Koller

LLMs are being increasingly used for planning-style tasks, but their capabilities for planning and reasoning are poorly understood.

Predicting generalization performance with correctness discriminators

no code implementations15 Nov 2023 Yuekun Yao, Alexander Koller

We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for the unseen data.

Semantic Parsing

ADaPT: As-Needed Decomposition and Planning with Language Models

no code implementations8 Nov 2023 Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot

Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment.

Decision Making

SLOG: A Structural Generalization Benchmark for Semantic Parsing

1 code implementation23 Oct 2023 Bingzhi Li, Lucia Donatelli, Alexander Koller, Tal Linzen, Yuekun Yao, Najoung Kim

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions.

Semantic Parsing

Closing the Curious Case of Neural Text Degeneration

1 code implementation2 Oct 2023 Matthew Finlayson, John Hewitt, Alexander Koller, Swabha Swayamdipta, Ashish Sabharwal

We provide a theoretical explanation for the effectiveness of the truncation sampling by proving that truncation methods that discard tokens below some probability threshold (the most common type of truncation) can guarantee that all sampled tokens have nonzero true probability.

Text Generation

Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation

no code implementations1 Oct 2023 Matthias Lindemann, Alexander Koller, Ivan Titov

Strong inductive biases enable learning from little data and help generalization outside of the training distribution.

Few-Shot Learning Inductive Bias +1

Compositional Generalization without Trees using Multiset Tagging and Latent Permutations

1 code implementation26 May 2023 Matthias Lindemann, Alexander Koller, Ivan Titov

Our model outperforms pretrained seq2seq models and prior work on realistic semantic parsing tasks that require generalization to longer examples.

Inductive Bias Semantic Parsing +1

What's the Meaning of Superhuman Performance in Today's NLU?

no code implementations15 May 2023 Simone Tedeschi, Johan Bos, Thierry Declerck, Jan Hajic, Daniel Hershcovich, Eduard H. Hovy, Alexander Koller, Simon Krek, Steven Schockaert, Rico Sennrich, Ekaterina Shutova, Roberto Navigli

In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension.

Position Reading Comprehension

We're Afraid Language Models Aren't Modeling Ambiguity

1 code implementation27 Apr 2023 Alisa Liu, Zhaofeng Wu, Julian Michael, Alane Suhr, Peter West, Alexander Koller, Swabha Swayamdipta, Noah A. Smith, Yejin Choi

We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset.


Structural generalization is hard for sequence-to-sequence models

1 code implementation24 Oct 2022 Yuekun Yao, Alexander Koller

Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure.

Semantic Parsing

Compositional Generalisation with Structured Reordering and Fertility Layers

1 code implementation6 Oct 2022 Matthias Lindemann, Alexander Koller, Ivan Titov

Seq2seq models have been shown to struggle with compositional generalisation, i. e. generalising to new and potentially more complex structures than seen during training.

Semantic Parsing

Compositional Generalization Requires Compositional Parsers

no code implementations24 Feb 2022 Pia Weißenhorn, Yuekun Yao, Lucia Donatelli, Alexander Koller

A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences.

Script Parsing with Hierarchical Sequence Modelling

no code implementations Joint Conference on Lexical and Computational Semantics 2021 Fangzhou Zhai, Iza {\v{S}}krjanec, Alexander Koller

A crucial step for the exploitation of script knowledge is script parsing, the task of tagging a text with the events and participants from a certain activity.

Story Generation Transfer Learning

Learning compositional structures for semantic graph parsing

1 code implementation ACL (spnlp) 2021 Jonas Groschwitz, Meaghan Fowlie, Alexander Koller

AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality.

Dependency Parsing

Generating Instructions at Different Levels of Abstraction

no code implementations COLING 2020 Arne Köhn, Julia Wichlacz, Álvaro Torralba, Daniel Höller, Jörg Hoffmann, Alexander Koller

When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction.


Fast semantic parsing with well-typedness guarantees

1 code implementation EMNLP 2020 Matthias Lindemann, Jonas Groschwitz, Alexander Koller

AM dependency parsing is a linguistically principled method for neural semantic parsing with high accuracy across multiple graphbanks.

Dependency Parsing Semantic Parsing

Normalizing Compositional Structures Across Graphbanks

1 code implementation COLING 2020 Lucia Donatelli, Jonas Groschwitz, Alexander Koller, Matthias Lindemann, Pia Weißenhorn

The emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure.

Multi-Task Learning Semantic Parsing

Semantic expressive capacity with bounded memory

no code implementations ACL 2019 Antoine Venant, Alexander Koller

We investigate the capacity of mechanisms for compositional semantic parsing to describe relations between sentences and semantic representations.

Semantic Parsing

Compositional Semantic Parsing Across Graphbanks

1 code implementation ACL 2019 Matthias Lindemann, Jonas Groschwitz, Alexander Koller

Most semantic parsers that map sentences to graph-based meaning representations are hand-designed for specific graphbanks.

Multi-Task Learning Semantic Parsing

Generalized chart constraints for efficient PCFG and TAG parsing

no code implementations ACL 2018 Stefan Grünewald, Sophie Henning, Alexander Koller

Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs.


Discovering User Groups for Natural Language Generation

no code implementations WS 2018 Nikos Engonopoulos, Christoph Teichmann, Alexander Koller

We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups.

Referring Expression Text Generation

AMR Dependency Parsing with a Typed Semantic Algebra

no code implementations ACL 2018 Jonas Groschwitz, Matthias Lindemann, Meaghan Fowlie, Mark Johnson, Alexander Koller

We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph.

Dependency Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.