Search Results for author:
Found 48 papers, 24 papers with code
Mining Health-related Cause-Effect Statements with High Precision at Large Scale
An efficient assessment of the health relatedness of text passages is important to mine the web at scale to conduct health sociological analyses or to develop a health search engine.
CausalQA: A Benchmark for Causal Question Answering
At least 5% of questions submitted to search engines ask about cause-effect relationships in some way.
Task Proposal: Abstractive Snippet Generation for Web Pages
We propose a shared task on abstractive snippet generation for web pages, a novel task of generating query-biased abstractive summaries for documents that are to be shown on a search results page.
Lightning IR: Straightforward Fine-tuning and Inference of Transformer-based Language Models for Information Retrieval
A wide range of transformer-based language models have been proposed for information retrieval tasks.
Systematic Evaluation of Neural Retrieval Models on the Touché 2020 Argument Retrieval Subset of BEIR
Our black-box evaluation reveals an inherent bias of neural models towards retrieving short passages from the Touch\'e 2020 data, and we also find that quite a few of the neural models' results are unjudged in the Touch\'e 2020 data.
A Systematic Investigation of Distilling Large Language Models into Cross-Encoders for Passage Re-ranking
Cross-encoders distilled from large language models (LLMs) are often more effective re-rankers than cross-encoders fine-tuned on manually labeled data.
Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders
Existing cross-encoder re-rankers can be categorized as pointwise, pairwise, or listwise models.
Task-Oriented Paraphrase Analytics
Since paraphrasing is an ill-defined task, the term "paraphrasing" covers text transformation tasks with different characteristics.
Analyzing Adversarial Attacks on Sequence-to-Sequence Relevance Models
Modern sequence-to-sequence relevance models like monoT5 can effectively capture complex textual interactions between queries and documents through cross-encoding.
Detecting Generated Native Ads in Conversational Search
In this paper, we thus take a first step to investigate whether LLMs can also be used as a countermeasure, i. e., to block generated native ads.
Investigating the Effects of Sparse Attention on Cross-Encoders
Cross-encoders are effective passage and document re-rankers but less efficient than other neural or classic retrieval models.
Evaluating Generative Ad Hoc Information Retrieval
To lay a foundation for developing new evaluation methods for generative retrieval systems, we survey the relevant literature from the fields of information retrieval and natural language processing, identify search tasks and system architectures in generative retrieval, develop a new user model, and study its operationalization.
The Information Retrieval Experiment Platform
Standardization is achieved when a retrieval approach implements PyTerrier's interfaces and the input and output of an experiment are compatible with ir_datasets and ir_measures.
Perspectives on Large Language Models for Relevance Judgment
When asked, large language models (LLMs) like ChatGPT claim that they can assist with relevance judgments but it is not clear whether automated judgments can reliably be used in evaluations of retrieval systems.
The Archive Query Log: Mining Millions of Search Result Pages of Hundreds of Search Engines from 25 Years of Web Archives
The Archive Query Log (AQL) is a previously unused, comprehensive query log collected at the Internet Archive over the last 25 years.
Paraphrase Acquisition from Image Captions
We propose to use image captions from the Web as a previously underutilized resource for paraphrases (i. e., texts with the same "message") and to create and analyze a corresponding dataset.
Sparse Pairwise Re-ranking with Pre-trained Transformers
Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences.
How Train-Test Leakage Affects Zero-shot Retrieval
We investigate the impact of this unintended train-test leakage by training neural retrieval models on combinations of a fixed number of MS MARCO / ORCAS queries that are highly similar to the actual test queries and an increasing number of other queries.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Clickbait Spoiling via Question Answering and Passage Retrieval
We introduce and study the task of clickbait spoiling: generating a short text that satisfies the curiosity induced by a clickbait post.
The Impact of Main Content Extraction on Near-Duplicate Detection
Commercial web search engines employ near-duplicate detection to ensure that users see each relevant result only once, albeit the underlying web crawls typically include (near-)duplicates of many web pages.
Towards Axiomatic Explanations for Neural Ranking Models
We investigate whether one can explain the behavior of neural ranking models in terms of their congruence with well understood principles of document ranking by using established theories from axiomatic IR.
Query Interpretations from Entity-Linked Segmentations
Web search queries can be ambiguous: is "source of the nile" meant to find information on the actual river or on a board game of that name?
Efficient Pairwise Annotation of Argument Quality
We present an efficient annotation framework for argument quality, a feature difficult to be measured reliably as per previous work.
The Importance of Suppressing Domain Style in Authorship Analysis
The prerequisite of many approaches to authorship analysis is a representation of writing style.
Conversational Search -- A Report from Dagstuhl Seminar 19461
Dagstuhl Seminar 19461 "Conversational Search" was held on 10-15 November 2019.
Abstractive Snippet Generation
An abstractive snippet is an originally created piece of text to summarize a web page on a search engine results page.
Ranked #1 on
Text Summarization
on Webis-Snippet-20 Corpus
Common Conversational Community Prototype: Scholarly Conversational Assistant
This paper discusses the potential for creating academic resources (tools, data, and evaluation approaches) to support research in conversational search, by focusing on realistic information needs and conversational interactions.
Unraveling the Search Space of Abusive Language in Wikipedia with Dynamic Lexicon Acquisition
Many discussions on online platforms suffer from users offending others by using abusive terminology, threatening each other, or being sarcastic.
Bias Analysis and Mitigation in the Evaluation of Authorship Verification
The PAN series of shared tasks is well known for its continuous and high quality research in the field of digital text forensics.
TARGER: Neural Argument Mining at Your Fingertips
We present TARGER, an open source neural argument mining framework for tagging arguments in free input texts and for keyword-based retrieval of arguments from an argument-tagged web-scale corpus.
Heuristic Authorship Obfuscation
Authorship verification is the task of determining whether two texts were written by the same author.
Generalizing Unmasking for Short Texts
Authorship verification is the problem of inferring whether two texts were written by the same author.
Answering Comparative Questions: Better than Ten-Blue-Links?
We present CAM (comparative argumentative machine), a novel open-domain IR system to argumentatively compare objects with respect to information extracted from the Common Crawl.
The Clickbait Challenge 2017: Towards a Regression Model for Clickbait Strength
Clickbait has grown to become a nuisance to social media users and social media operators alike.
Categorizing Comparative Sentences
We tackle the tasks of automatically identifying comparative sentences and categorizing the intended preference (e. g., "Python has better NLP libraries than MATLAB" => (Python, better, MATLAB).
Crowdsourcing a Large Corpus of Clickbait on Twitter
To address the urging task of clickbait detection, we constructed a new corpus of 38, 517 annotated Twitter tweets, the Webis Clickbait Corpus 2017.
Modeling Deliberative Argumentation Strategies on Wikipedia
This paper studies how the argumentation strategies of participants in deliberative discussions can be supported computationally.
Heuristic Feature Selection for Clickbait Detection
We study feature selection as a means to optimize the baseline clickbait detector employed at the Clickbait Challenge 2017.
Patterns of Argumentation Strategies across Topics
This paper presents an analysis of argumentation strategies in news editorials within and across topics.
A News Editorial Corpus for Mining Argumentation Strategies
Many argumentative texts, and news editorials in particular, follow a specific strategy to persuade their readers of some opinion or attitude.
