Pinelopi Papalampidi


2023

pdf bib
Hierarchical3D Adapters for Long Video-to-text Summarization
Pinelopi Papalampidi | Mirella Lapata
Findings of the Association for Computational Linguistics: EACL 2023

In this paper, we focus on video-to-text summarization and investigate how to best utilize multimodal information for summarizing long inputs (e.g., an hour-long TV show) into long outputs (e.g., a multi-sentence summary). We extend SummScreen (Chen et al., 2022), a dialogue summarization dataset consisting of transcripts of TV episodes with reference summaries, and create a multimodal variant by collecting corresponding full-length videos. We incorporate multimodal information into a pre-trained textual summarizer efficiently using adapter modules augmented with a hierarchical structure while tuning only 3.8% of model parameters. Our experiments demonstrate that multimodal information offers superior performance over more memory-heavy and fully fine-tuned textual summarization methods.

2020

pdf bib
Screenplay Summarization Using Latent Narrative Structure
Pinelopi Papalampidi | Frank Keller | Lea Frermann | Mirella Lapata
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Most general-purpose extractive summarization models are trained on news articles, which are short and present all important information upfront. As a result, such models are biased on position and often perform a smart selection of sentences from the beginning of the document. When summarizing long narratives, which have complex structure and present information piecemeal, simple position heuristics are not sufficient. In this paper, we propose to explicitly incorporate the underlying structure of narratives into general unsupervised and supervised extractive summarization models. We formalize narrative structure in terms of key narrative events (turning points) and treat it as latent in order to summarize screenplays (i.e., extract an optimal sequence of scenes). Experimental results on the CSI corpus of TV screenplays, which we augment with scene-level summarization labels, show that latent turning points correlate with important aspects of a CSI episode and improve summarization performance over general extractive algorithms leading to more complete and diverse summaries.

2019

pdf bib
Movie Plot Analysis via Turning Point Identification
Pinelopi Papalampidi | Frank Keller | Mirella Lapata
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

According to screenwriting theory, turning points (e.g., change of plans, major setback, climax) are crucial narrative moments within a screenplay: they define the plot structure, determine its progression and segment the screenplay into thematic units (e.g., setup, complications, aftermath). We propose the task of turning point identification in movies as a means of analyzing their narrative structure. We argue that turning points and the segmentation they provide can facilitate processing long, complex narratives, such as screenplays, for summarization and question answering. We introduce a dataset consisting of screenplays and plot synopses annotated with turning points and present an end-to-end neural network model that identifies turning points in plot synopses and projects them onto scenes in screenplays. Our model outperforms strong baselines based on state-of-the-art sentence representations and the expected position of turning points.

2018

pdf bib
NTUA-SLP at SemEval-2018 Task 3: Tracking Ironic Tweets using Ensembles of Word and Character Level Attentive RNNs
Christos Baziotis | Athanasiou Nikolaos | Pinelopi Papalampidi | Athanasia Kolovou | Georgios Paraskevopoulos | Nikolaos Ellinas | Alexandros Potamianos
Proceedings of the 12th International Workshop on Semantic Evaluation

In this paper we present two deep-learning systems that competed at SemEval-2018 Task 3 “Irony detection in English tweets”. We design and ensemble two independent models, based on recurrent neural networks (Bi-LSTM), which operate at the word and character level, in order to capture both the semantic and syntactic information in tweets. Our models are augmented with a self-attention mechanism, in order to identify the most informative words. The embedding layer of our word-level model is initialized with word2vec word embeddings, pretrained on a collection of 550 million English tweets. We did not utilize any handcrafted features, lexicons or external datasets as prior information and our models are trained end-to-end using back propagation on constrained data. Furthermore, we provide visualizations of tweets with annotations for the salient tokens of the attention layer that can help to interpret the inner workings of the proposed models. We ranked 2nd out of 42 teams in Subtask A and 2nd out of 31 teams in Subtask B. However, post-task-completion enhancements of our models achieve state-of-the-art results ranking 1st for both subtasks.

2017

pdf bib
Tweester at SemEval-2017 Task 4: Fusion of Semantic-Affective and pairwise classification models for sentiment analysis in Twitter
Athanasia Kolovou | Filippos Kokkinos | Aris Fergadis | Pinelopi Papalampidi | Elias Iosif | Nikolaos Malandrakis | Elisavet Palogiannidi | Haris Papageorgiou | Shrikanth Narayanan | Alexandros Potamianos
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)

In this paper, we describe our submission to SemEval2017 Task 4: Sentiment Analysis in Twitter. Specifically the proposed system participated both to tweet polarity classification (two-, three- and five class) and tweet quantification (two and five-class) tasks.